Paper Digest: Recent Papers on Machine Translation
Paper Digest Team extracted all recent Machine Translation related papers on our radar, and generated highlight sentences for them. The results are then sorted by relevance & date. In addition to this ‘static’ page, we also provide a real-time version of this article, which has more coverage and is updated in real time to include the most recent updates on this topic.
This list is created by the Paper Digest Team. Experience the cutting-edge capabilities of Paper Digest, an innovative AI-powered research platform that empowers you to read, write, get answers and review.
Try us today and unlock the full potential of our services for free!
TABLE 1: Paper Digest: Recent Papers on Machine Translation
| Paper | Author(s) | Source | Date | |
|---|---|---|---|---|
| 1 | Investigating Numerical Translation with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study focuses on evaluating the reliability of LLM-based machine translation systems when handling numerical data. |
WEI TANG et. al. | arxiv-cs.CL | 2025-01-08 |
| 2 | Quality Estimation Based Feedback Training for Improving Pronoun Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Pronoun translation is a longstanding challenge in neural machine translation (NMT), often requiring inter-sentential context to ensure linguistic accuracy. To address this, we introduce ProNMT, a novel framework designed to enhance pronoun and overall translation quality in context-aware machine translation systems. |
Harshit Dhankhar; Baban Gain; Asif Ekbal; Yogesh Mani Tripathi; | arxiv-cs.CL | 2025-01-06 |
| 3 | Adaptive Few-shot Prompting for Machine Translation with Pre-trained Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, existing evidence shows that LLMs are prompt-sensitive and it is sub-optimal to apply the fixed prompt to any input for downstream machine translation tasks. To address this issue, we propose an adaptive few-shot prompting (AFSP) framework to automatically select suitable translation demonstrations for various source input sentences to further elicit the translation capability of an LLM for better machine translation. |
Lei Tang; Jinghui Qin; Wenxuan Ye; Hao Tan; Zhijing Yang; | arxiv-cs.CL | 2025-01-03 |
| 4 | Crossing Language Borders: A Pipeline for Indonesian Manhwa Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this project, we develop a practical and efficient solution for automating the Manhwa translation from Indonesian to English. |
Nithyasri Narasimhan; Sagarika Singh; | arxiv-cs.LG | 2025-01-02 |
| 5 | Advancing Explainability in Neural Machine Translation: Analytical Metrics for Attention and Alignment Consistency Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The interpretability of these models, especially their internal attention mechanisms, is critical for building trust and verifying that these systems behave as intended. In this work, we introduce a systematic framework to quantitatively evaluate the explainability of an NMT model attention patterns by comparing them against statistical alignments and correlating them with standard machine translation quality metrics. |
Anurag Mishra; | arxiv-cs.AI | 2024-12-24 |
| 6 | Multiple References with Meaningful Variations Improve Literary Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We classify the semantic similarity between paraphrases into three groups: low, medium, and high, and fine-tune two different LLMs (mT5-large and LLaMA-2-7B) for downstream MT tasks. |
Si Wu; John Wieting; David A. Smith; | arxiv-cs.CL | 2024-12-24 |
| 7 | Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduced GIST, a large-scale multilingual AI terminology dataset containing 5K terms extracted from top AI conference papers spanning 2000 to 2023. |
JIARUI LIU et. al. | arxiv-cs.CL | 2024-12-24 |
| 8 | RepoTransBench: A Real-World Benchmark for Repository-Level Code Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Such benchmarks do not accurately reflect real-world demands, where entire repositories often need to be translated, involving longer code length and more complex functionalities. To address this gap, we propose a new benchmark, named RepoTransBench, which is a real-world repository-level code translation benchmark with an automatically executable test suite. |
YANLI WANG et. al. | arxiv-cs.SE | 2024-12-23 |
| 9 | Investigating Length Issues in Document-level Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we challenge the ability of MT systems to handle texts comprising up to several thousands of tokens. |
Ziqian Peng; Rachel Bawden; François Yvon; | arxiv-cs.CL | 2024-12-23 |
| 10 | Ensuring Consistency for In-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The former entails incorporating image information during translation, while the latter involves maintaining consistency between the style of the text-image and the original image, ensuring background integrity. To address these consistency requirements, we introduce a novel two-stage framework named HCIIT (High-Consistency In-Image Translation) which involves text-image translation using a multimodal multilingual large language model in the first stage and image backfilling with a diffusion model in the second stage. |
CHENGPENG FU et. al. | arxiv-cs.CL | 2024-12-23 |
| 11 | A Thorough Investigation Into The Application of Deep CNN for Enhancing Natural Language Processing Capabilities Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, traditional NLP models struggle with accuracy and efficiency. This paper introduces Deep Convolutional Neural Networks (DCNN) into NLP to address these issues. |
CHANG WENG et. al. | arxiv-cs.CL | 2024-12-20 |
| 12 | Mention Attention for Pronoun Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We assume that extracting additional mention features can help pronoun translation. Therefore, we introduce an additional mention attention module in the decoder to pay extra attention to source mentions but not non-mention tokens. |
Gongbo Tang; Christian Hardmeier; | arxiv-cs.CL | 2024-12-19 |
| 13 | Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Why do we build local large language models (LLMs)? |
KOSHIRO SAITO et. al. | arxiv-cs.CL | 2024-12-18 |
| 14 | Understanding and Analyzing Model Robustness and Knowledge-Transfer in Multilingual Neural Machine Translation Using TX-Ray Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, Multilingual Neural Machine Translation (MNMT) in extremely low-resource settings remains underexplored. This research investigates how knowledge transfer across languages can enhance MNMT in such scenarios. |
Vageesh Saxena; Sharid Loáiciga; Nils Rethmeier; | arxiv-cs.CL | 2024-12-18 |
| 15 | Language VerY Rare for All Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce LYRA (Language verY Rare for All), a novel approach that combines open LLM fine-tuning, retrieval-augmented generation (RAG), and transfer learning from related high-resource languages. |
Ibrahim Merad; Amos Wolf; Ziad Mazzawi; Yannick Léo; | arxiv-cs.CL | 2024-12-18 |
| 16 | The Role of Handling Attributive Nouns in Improving Chinese-To-English Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we specifically target the translation challenges posed by attributive nouns in Chinese, which frequently cause ambiguities in English translation. |
Lisa Wang; Adam Meyers; John E. Ortega; Rodolfo Zevallos; | arxiv-cs.CL | 2024-12-18 |
| 17 | Findings of The WMT 2024 Shared Task on Discourse-Level Literary Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We focus on three language directions: Chinese-English, Chinese-German, and Chinese-Russian, with the latter two ones newly added. |
LONGYUE WANG et. al. | arxiv-cs.CL | 2024-12-16 |
| 18 | Analyzing The Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we investigate the role of attention heads in Context-aware Machine Translation models for pronoun disambiguation in the English-to-German and English-to-French language directions. |
Paweł Mąka; Yusuf Can Semerci; Jan Scholtes; Gerasimos Spanakis; | arxiv-cs.CL | 2024-12-15 |
| 19 | A Comparative Study of LLMs, NMT Models, and Their Combination in Persian-English Idiom Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper introduces two parallel datasets of sentences containing idiomatic expressions for Persian$\rightarrow$English and English$\rightarrow$Persian translations, with Persian idioms sampled from our PersianIdioms resource, a collection of 2,200 idioms and their meanings. |
Sara Rezaeimanesh; Faezeh Hosseini; Yadollah Yaghoobzadeh; | arxiv-cs.CL | 2024-12-13 |
| 20 | Shiksha: A Technical Domain Focused Translation Dataset and Model for Indian Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Finding a translation dataset that tends to these domains in particular, poses a difficult challenge. In this paper, we address this by creating a multilingual parallel corpus containing more than 2.8 million rows of English-to-Indic and Indic-to-Indic high-quality translation pairs across 8 Indian languages. |
Advait Joglekar; Srinivasan Umesh; | arxiv-cs.CL | 2024-12-12 |
| 21 | Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Inspired by the reinforcement learning from human feedback framework, we introduce a novel method that rewards both naturalness and content preservation. |
Huiyuan Lai; Esther Ploeger; Rik van Noord; Antonio Toral; | arxiv-cs.CL | 2024-12-11 |
| 22 | Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we compare the domain-specific translation performance of open-source autoregressive decoder-only large language models (LLMs) with task-oriented machine translation (MT) models. |
Aman Kassahun Wassie; Mahdi Molaei; Yasmin Moslem; | arxiv-cs.CL | 2024-12-08 |
| 23 | BhashaVerse : Translation Ecosystem for Indian Subcontinent Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper focuses on developing translation models and related applications for 36 Indian languages, including Assamese, Awadhi, Bengali, Bhojpuri, Braj, Bodo, Dogri, English, Konkani, Gondi, Gujarati, Hindi, Hinglish, Ho, Kannada, Kangri, Kashmiri (Arabic and Devanagari), Khasi, Mizo, Magahi, Maithili, Malayalam, Marathi, Manipuri (Bengali and Meitei), Nepali, Oriya, Punjabi, Sanskrit, Santali, Sinhala, Sindhi (Arabic and Devanagari), Tamil, Tulu, Telugu, and Urdu. |
Vandan Mujadia; Dipti Misra Sharma; | arxiv-cs.CL | 2024-12-05 |
| 24 | Representation Purification for End-to-End Speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we conceptualize speech representation as a combination of content-agnostic and content-relevant factors. |
Chengwei Zhang; Yue Zhou; Rui Zhao; Yidong Chen; Xiaodong Shi; | arxiv-cs.CL | 2024-12-05 |
| 25 | Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper explores the transformative role of Agent AI and LangGraph in advancing the automation and effectiveness of machine translation (MT). |
Jialin Wang; Zhihua Duan; | arxiv-cs.CL | 2024-12-04 |
| 26 | A 2-step Framework for Automated Literary Translation Evaluation: Its Promises and Pitfalls Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose and evaluate the feasibility of a two-stage pipeline to evaluate literary machine translation, in a fine-grained manner, from English to Korean. |
SHEIKH SHAFAYAT et. al. | arxiv-cs.CL | 2024-12-02 |
| 27 | A Multi-way Parallel Named Entity Annotated Corpus for English, Tamil and Sinhala Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents a multi-way parallel English-Tamil-Sinhala corpus annotated with Named Entities (NEs), where Sinhala and Tamil are low-resource languages. |
SURANGIKA RANATHUNGA et. al. | arxiv-cs.CL | 2024-12-02 |
| 28 | Towards Santali Linguistic Inclusion: Building The First Santali-to-English Translation Model Using MT5 Transformer and Data Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our paper aims to include Santali to the NPL spectrum. |
SYED MOHAMMED MOSTAQUE BILLAH et. al. | arxiv-cs.CL | 2024-11-29 |
| 29 | Aligning Pre-trained Models for Spoken Language Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper investigates a novel approach to end-to-end speech translation (ST) based on aligning frozen pre-trained automatic speech recognition (ASR) and machine translation (MT) models via a small connector module (Q-Former, our Subsampler-Transformer Encoder). |
Šimon Sedláček; Santosh Kesiraju; Alexander Polok; Jan Černocký; | arxiv-cs.CL | 2024-11-27 |
| 30 | SwissADT: An Audio Description Translation System for Swiss Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: By collecting well-crafted AD data augmented with video clips in German, French, Italian, and English, and leveraging the power of Large Language Models (LLMs), we aim to enhance information accessibility for diverse language populations in Switzerland by automatically translating AD scripts to the desired Swiss language. |
Lukas Fischer; Yingqiang Gao; Alexa Lintner; Sarah Ebling; | arxiv-cs.CL | 2024-11-22 |
| 31 | Benchmarking GPT-4 Against Human Translators: A Comprehensive Evaluation Across Languages, Domains, and Expertise Levels Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This study presents a comprehensive evaluation of GPT-4’s translation capabilities compared to human translators of varying expertise levels. |
JIANHAO YAN et. al. | arxiv-cs.CL | 2024-11-20 |
| 32 | A Comparative Study of Text Retrieval Models on DaReCzech Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This article presents a comprehensive evaluation of 7 off-the-shelf document retrieval models: Splade, Plaid, Plaid-X, SimCSE, Contriever, OpenAI ADA and Gemma2 chosen to determine their performance on the Czech retrieval dataset DaReCzech. |
Jakub Stetina; Martin Fajcik; Michal Stefanik; Michal Hradis; | arxiv-cs.IR | 2024-11-19 |
| 33 | Chain-of-Dictionary Prompting Elicits Translation in Large Language Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we present a novel framework, CoD, Chain-of-Dictionary Prompting, which augments LLMs with prior knowledge with the chains of multilingual dictionaries for a subset of input words to elicit translation abilities for LLMs. |
HONGYUAN LU et. al. | emnlp | 2024-11-11 |
| 34 | MiTTenS: A Dataset for Evaluating Gender Mistranslation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Translation systems, including foundation models capable of translation, can produce errors that result in gender mistranslation, and such errors can be especially harmful. To measure the extent of such potential harms when translating into and out of English, we introduce a dataset, MiTTenS, covering 26 languages from a variety of language families and scripts, including several traditionally under-represented in digital resources. |
Kevin Robinson; Sneha Kudugunta; Romina Stella; Sunipa Dev; Jasmijn Bastings; | emnlp | 2024-11-11 |
| 35 | Using Language Models to Disambiguate Lexical Choices in Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We work with native speakers of nine languages to create DTAiLS, a dataset of 1,377 sentence pairs that exhibit cross-lingual concept variation when translating from English. |
Josh Barua; Sanjay Subramanian; Kayo Yin; Alane Suhr; | emnlp | 2024-11-11 |
| 36 | SpeechQE: Estimating The Quality of Direct Speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we formulate the task of quality estimation for speech translation (SpeechQE), construct a benchmark, and evaluate a family of systems based on cascaded and end-to-end architectures. |
HyoJung Han; Kevin Duh; Marine Carpuat; | emnlp | 2024-11-11 |
| 37 | Reconsidering Sentence-Level Sign Language Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Historically, sign language machine translation has been posed as a sentence-level task: datasets consisting of continuous narratives are chopped up and presented to the model as isolated clips. In this work, we explore the limitations of this task framing. |
Garrett Tanzer; Maximus Shengelia; Ken Harrenstien; David Uthus; | emnlp | 2024-11-11 |
| 38 | Error Analysis of Multilingual Language Models in Machine Translation: A Case Study of English-Amharic Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We employed both automatic and human evaluation methods to analyze translation errors. |
Hizkiel Mitiku Alemayehu; Hamada M Zahera; Axel-Cyrille Ngonga Ngomo; | emnlp | 2024-11-11 |
| 39 | Isochrony-Controlled Speech-to-Text Translation: A Study on Translating from Sino-Tibetan to Indo-European Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Previous methods often controlled the number of words or characters generated by the Machine Translation model to approximate the source sentence’s length without considering the isochrony of pauses and speech segments, as duration can vary between languages. To address this, we present improvements to the duration alignment component of our sequence-to-sequence ST model. |
MIDIA YOUSEFI et. al. | arxiv-cs.CL | 2024-11-11 |
| 40 | Building Resources for Emakhuwa: Machine Translation and News Classification Benchmarks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a comprehensive collection of NLP resources for Emakhuwa, Mozambique’s most widely spoken language. |
Felermino D. M. A. Ali; Henrique Lopes Cardoso; Rui Sousa-Silva; | emnlp | 2024-11-11 |
| 41 | Fine-Tuning Large Language Models to Translate: Will A Touch of Noisy Data in Misaligned Languages Suffice? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Traditionally, success in multilingual machine translation can be attributed to three key factors in training data: large volume, diverse translation directions, and high quality. In the current practice of fine-tuning large language models (LLMs) for translation, we revisit the importance of these factors. |
DAWEI ZHU et. al. | emnlp | 2024-11-11 |
| 42 | What Do Large Language Models Need for Machine Translation Evaluation? Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we explore what translation information, such as the source, reference, translation errors and annotation guidelines, is needed for LLMs to evaluate MT quality. |
SHENBIN QIAN et. al. | emnlp | 2024-11-11 |
| 43 | Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address the problem of cross-cultural translation on two fronts: (i) we introduce XC-Translate, the first large-scale, manually-created benchmark for machine translation that focuses on text that contains potentially culturally-nuanced entity names, and (ii) we propose KG-MT, a novel end-to-end method to integrate information from a multilingual knowledge graph into a neural machine translation model by leveraging a dense retrieval mechanism. |
SIMONE CONIA et. al. | emnlp | 2024-11-11 |
| 44 | CULL-MT: Compression Using Language and Layer Pruning for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present CULL-MT, a compression method for machine translation models based on structural layer pruning and selected language directions. |
Pedram Rostami; Mohammad Javad Dousti; | arxiv-cs.CL | 2024-11-10 |
| 45 | Fineweb-Edu-Ar: Machine-translated Corpus to Support Arabic Small Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This report introduces FineWeb-Edu-Ar, a machine-translated version of the exceedingly popular (deduplicated) FineWeb-Edu dataset from HuggingFace. |
Sultan Alrashed; Dmitrii Khizbullin; David R. Pugh; | arxiv-cs.CL | 2024-11-10 |
| 46 | Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present a series of advanced explorations of Transformer architecture design to minimize the error compared to the true “solution.” |
BEI LI et. al. | arxiv-cs.CL | 2024-11-05 |
| 47 | Context-Informed Machine Translation of Manga Using Multimodal Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we investigate to what extent multimodal large language models (LLMs) can provide effective manga translation, thereby assisting manga authors and publishers in reaching wider audiences. |
Philip Lippmann; Konrad Skublicki; Joshua Tanner; Shonosuke Ishiwatari; Jie Yang; | arxiv-cs.CL | 2024-11-04 |
| 48 | Language Models and Cycle Consistency for Self-Reflective Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a novel framework that leverages large language models (LLMs) for machine translation (MT). |
Jianqiao Wangni; | arxiv-cs.CL | 2024-11-04 |
| 49 | MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation Via Human Preference Calibration Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present MetaMetrics-MT, an innovative metric designed to evaluate machine translation (MT) tasks by aligning closely with human preferences through Bayesian optimization with Gaussian Processes. |
David Anugraha; Garry Kuwanto; Lucky Susanto; Derry Tanti Wijaya; Genta Indra Winata; | arxiv-cs.CL | 2024-11-01 |
| 50 | Anticipating Future with Large Language Model for Simultaneous Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Motivated by human interpreters’ technique to forecast future words before hearing them, we propose $\textbf{T}$ranslation by $\textbf{A}$nticipating $\textbf{F}$uture (TAF), a method to improve translation quality while retraining low latency. |
SIQI OUYANG et. al. | arxiv-cs.CL | 2024-10-29 |
| 51 | GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce GrammaMT, a grammatically-aware prompting approach for machine translation that uses Interlinear Glossed Text (IGT), a common form of linguistic description providing morphological and lexical annotations for source sentences. |
Rita Ramos; Everlyn Asiko Chimoto; Maartje ter Hoeve; Natalie Schluter; | arxiv-cs.CL | 2024-10-24 |
| 52 | Dialectal and Low-Resource Machine Translation for Aromanian Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The primary contribution of this research is twofold: (1) the creation of the most extensive Aromanian-Romanian parallel corpus to date, consisting of 79,000 sentence pairs, and (2) the development and comparative analysis of several machine translation models optimized for Aromanian. |
Alexandru-Iulius Jerpelea; Alina Rădoi; Sergiu Nisioi; | arxiv-cs.CL | 2024-10-23 |
| 53 | Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Large language models (LLMs) perform well on common tasks but struggle with generalization in low-resource and low-computation settings. We examine this limitation by testing various LLMs and specialized translation models on English-Thai machine translation and code-switching datasets. |
JIRAT CHIARANAIPANICH et. al. | arxiv-cs.CL | 2024-10-22 |
| 54 | Learning from Others’ Mistakes: Finetuning Machine Translation Models with Span-level Error Annotations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we explore the potential of utilizing fine-grained span-level annotations from offline datasets to improve model quality. |
LILY H. ZHANG et. al. | arxiv-cs.CL | 2024-10-21 |
| 55 | On Creating An English-Thai Code-switched Machine Translation in Medical Domain Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Our research prioritizes not merely improving translation accuracy but also maintaining medical terminology in English within the translated text through code-switched (CS) translation. We developed a method to produce CS medical translation data, fine-tuned a CS translation model with this data, and evaluated its performance against strong baselines, such as Google Neural Machine Translation (NMT) and GPT-3.5/GPT-4. |
PARINTHAPAT PENGPUN et. al. | arxiv-cs.CL | 2024-10-21 |
| 56 | MHumanEval – A Multilingual Benchmark to Evaluate Large Language Models for Code Generation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Recent advancements in large language models (LLMs) have significantly enhanced code generation from natural language prompts. The HumanEval Benchmark, developed by OpenAI, … |
Nishat Raihan; Antonios Anastasopoulos; Marcos Zampieri; | ArXiv | 2024-10-19 |
| 57 | MHumanEval — A Multilingual Benchmark to Evaluate Large Language Models for Code Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While recent works have addressed test coverage and programming language (PL) diversity, code generation from low-resource language prompts remains largely unexplored. To address this gap, we introduce mHumanEval, an extended benchmark supporting prompts in over 200 natural languages. |
Nishat Raihan; Antonios Anastasopoulos; Marcos Zampieri; | arxiv-cs.CL | 2024-10-19 |
| 58 | Analyzing Context Utilization of LLMs in Document-Level Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate the ability of prominent LLMs to utilize context by analyzing models’ robustness to perturbed and randomized document context. |
Wafaa Mohammed; Vlad Niculae; | arxiv-cs.CL | 2024-10-18 |
| 59 | NLIP_Lab-IITH Multilingual MT System for WAT24 MT Shared Task Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper describes NLIP Lab’s multilingual machine translation system for the WAT24 shared task on multilingual Indic MT task for 22 scheduled languages belonging to 4 language families. |
Maharaj Brahma; Pramit Sahoo; Maunendra Sankar Desarkar; | arxiv-cs.CL | 2024-10-17 |
| 60 | Quantity Vs. Quality of Monolingual Source Data in Automatic Text Translation: Can It Be Too Little If It Is Too Good? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, it has been shown that too much of this data can be detrimental to the performance of the model if the available parallel data is comparatively extremely low. In this study, we investigate whether the monolingual data can also be too little and if this reduction, based on quality, has any effect on the performance of the translation model. |
Idris Abdulmumin; Bashir Shehu Galadanci; Garba Aliyu; Shamsuddeen Hassan Muhammad; | arxiv-cs.CL | 2024-10-17 |
| 61 | PMMT: Preference Alignment in Multilingual Machine Translation Via LLM Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, a new method is proposed to effectively generate large-scale multilingual parallel corpora with specific translation preferences using Large Language Models (LLMs). |
Shuqiao Sun; Yutong Yao; Peiwen Wu; Feijun Jiang; Kaifu Zhang; | arxiv-cs.CL | 2024-10-15 |
| 62 | IsoChronoMeter: A Simple and Effective Isochronic Translation Evaluation Metric Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Using ICM we demonstrate the shortcomings of state-of-the-art translation systems and show the need for new methods. |
Nikolai Rozanov; Vikentiy Pankov; Dmitrii Mukhutdinov; Dima Vypirailenko; | arxiv-cs.CL | 2024-10-14 |
| 63 | Machine Translation Evaluation Benchmark for Wu Chinese: Workflow and Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a FLORES+ dataset as an evaluation benchmark for modern Wu Chinese machine translation models and showcase its compatibility with existing Wu data. |
Hongjian Yu; Yiming Shi; Zherui Zhou; Christopher Haberland; | arxiv-cs.CL | 2024-10-14 |
| 64 | Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs’ Code-Mixing Capabilities Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce Rule-Based Prompting, a novel prompting technique to generate code-mixed sentences. |
Ayushman Gupta; Akhil Bhogal; Kripabandhu Ghosh; | arxiv-cs.CL | 2024-10-14 |
| 65 | Is Hate Lost in Translation?: Evaluation of Multilingual LGBTQIA+ Hate Speech Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper explores the challenges of detecting LGBTQIA+ hate speech of large language models across multiple languages, including English, Italian, Chinese and (code-switched) English-Tamil, examining the impact of machine translation and whether the nuances of hate speech are preserved across translation. |
Fai Leui Chan; Duke Nguyen; Aditya Joshi; | arxiv-cs.CL | 2024-10-14 |
| 66 | ChakmaNMT: A Low-resource Machine Translation On Chakma Language Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The geopolitical division between the indigenous Chakma population and mainstream Bangladesh creates a significant cultural and linguistic gap, as the Chakma community, mostly … |
AUNABIL CHAKMA et. al. | arxiv-cs.CL | 2024-10-14 |
| 67 | QE-EBM: Using Quality Estimators As Energy Loss for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose QE-EBM, a method of employing quality estimators as trainable loss networks that can directly backpropagate to the NMT model. |
Gahyun Yoo; Jay Yoon Lee; | arxiv-cs.CL | 2024-10-14 |
| 68 | Watching The Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The automatic assessment of translation quality has recently become crucial across several stages of the translation pipeline, from data curation to training and decoding. … |
Emmanouil Zaranis; Giuseppe Attanasio; Sweta Agrawal; André F. T. Martins; | arxiv-cs.CL | 2024-10-14 |
| 69 | Ukrainian-to-English Folktale Corpus: Parallel Corpus Creation and Augmentation for Machine Translation in Low-resource Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We have created a new Ukrainian-To-English parallel corpus of familiar Ukrainian folktales based on available English translations and suggested several new ones. We offer a combined domain-specific approach to building and augmenting this corpus, considering the nature of the domain and differences in the purpose of human versus machine translation. |
Olena Burda-Lassen; | arxiv-cs.CL | 2024-10-13 |
| 70 | NusaMT-7B: Machine Translation for Low-Resource Indonesian Languages with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces NusaMT-7B, an LLM-based machine translation model for low-resource Indonesian languages, starting with Balinese and Minangkabau. |
William Tan; Kevin Zhu; | arxiv-cs.CL | 2024-10-10 |
| 71 | Neural Machine Translation System for Lezgian, Russian and Azerbaijani Languages Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We contribute our translation model along with the collected parallel and monolingual corpora and sentence encoder for the Lezgian language. |
Alidar Asvarov; Andrey Grabovoy; | arxiv-cs.CL | 2024-10-07 |
| 72 | Translation Canvas: An Explainable Interface to Pinpoint and Analyze Translation Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, these tools provide limited insights for fine-grained system-level comparisons and the analysis of instance-level defects. To address these limitations, we introduce Translation Canvas, an explainable interface designed to pinpoint and analyze translation systems’ performance: 1) Translation Canvas assists machine translation researchers in comprehending system-level model performance by identifying common errors (their frequency and severity) and analyzing relationships between different systems based on various evaluation metrics. |
Chinmay Dandekar; Wenda Xu; Xi Xu; Siqi Ouyang; Lei Li; | arxiv-cs.CL | 2024-10-07 |
| 73 | Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present a series of advanced explorations of Transformer architecture design to minimize the error compared to the true “solution.” |
BEI LI et. al. | nips | 2024-10-07 |
| 74 | A Test Suite of Prompt Injection Attacks for LLM-based Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Specifically, the task is to translate questions from the TruthfulQA test suite, where an adversarial prompt is prepended to the questions, instructing the system to ignore the translation instruction and answer the questions instead. In this test suite, we extend this approach to all the language pairs of the WMT 2024 General Machine Translation task. |
Antonio Valerio Miceli-Barone; Zhifan Sun; | arxiv-cs.CL | 2024-10-07 |
| 75 | TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we introduce a novel model framework TransVIP that leverages diverse datasets in a cascade fashion yet facilitates end-to-end inference through joint probability. |
CHENYANG LE et. al. | nips | 2024-10-07 |
| 76 | CTC-GMM: CTC Guided Modality Matching for Fast and Accurate Streaming Speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce a methodology named Connectionist Temporal Classification guided modality matching (CTC-GMM) that enhances the streaming ST model by leveraging extensive machine translation (MT) text data. |
Rui Zhao; Jinyu Li; Ruchao Fan; Matt Post; | arxiv-cs.CL | 2024-10-07 |
| 77 | Efficient Minimum Bayes Risk Decoding Using Low-Rank Matrix Completion Algorithms Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents a novel approach for approximating MBR decoding using matrix completion techniques, focusing on a machine translation task. |
Firas Trabelsi; David Vilar; Mara Finkelstein; Markus Freitag; | nips | 2024-10-07 |
| 78 | QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we address the problem of sampling a set of high-quality and diverse translations. |
GONÇALO FARIA et. al. | nips | 2024-10-07 |
| 79 | Scaling Sign Language Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we push forward the frontier of SLT by scaling pretraining data, model size, and number of translation directions. |
Biao Zhang; Garrett Tanzer; Orhan Firat; | nips | 2024-10-07 |
| 80 | A Multi-task Learning Framework for Evaluating Machine Translation of Emotion-loaded User-generated Content Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We extend it with sentence-level evaluation scores and word-level labels, leading to a dataset suitable for sentence- and word-level translation evaluation and emotion classification, in a multi-task setting. We propose a new architecture to perform these tasks concurrently, with a novel combined loss function, which integrates different loss heuristics, like the Nash and Aligned losses. |
Shenbin Qian; Constantin Orăsan; Diptesh Kanojia; Félix do Carmo; | arxiv-cs.CL | 2024-10-04 |
| 81 | What Do Large Language Models Need for Machine Translation Evaluation? Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we explore what translation information, such as the source, reference, translation errors and annotation guidelines, is needed for LLMs to evaluate MT quality. |
SHENBIN QIAN et. al. | arxiv-cs.CL | 2024-10-04 |
| 82 | Cogs in A Machine, Doing What They’re Meant to Do — The AMI Submission to The WMT24 General Translation Task Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents the submission of the \’Arni Magnusson Institute’s team to the WMT24 General translation task. |
Atli Jasonarson; Hinrik Hafsteinsson; Bjarki Ármannsson; Steinþór Steingrímsson; | arxiv-cs.CL | 2024-10-04 |
| 83 | Cogs in A Machine, Doing What They’re Meant to Do – The AMI Submission to The WMT24 General Translation Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper presents the submission of the \’Arni Magnusson Institute’s team to the WMT24 General translation task. We work on the English->Icelandic translation direction. Our … |
Atli Jasonarson; Hinrik Hafsteinsson; Bjarki ‘Armannsson; Steinth’or Steingr’imsson; | ArXiv | 2024-10-04 |
| 84 | Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our evaluation of prominent LLMs reveals a discernible performance gap against traditional MT systems, highlighting domain overfitting and catastrophic forgetting issues after fine-tuning on domain-limited corpora. To mitigate this, we propose a domain Chain of Thought (CoT) fine-tuning technique that utilizes the intrinsic multi-domain intelligence of LLMs to improve translation performance. |
TIANXIANG HU et. al. | arxiv-cs.CL | 2024-10-03 |
| 85 | X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we prioritize quality over scaling number of languages, with a focus on multilingual machine translation task, and introduce X-ALMA, a model designed with a commitment to ensuring top-tier performance across 50 diverse languages, regardless of their resource levels. |
HAORAN XU et. al. | arxiv-cs.CL | 2024-10-03 |
| 86 | Efficient Technical Term Translation: A Knowledge Distillation Approach for Parenthetical Terminology Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper addresses the challenge of accurately translating technical terms, which are crucial for clear communication in specialized fields. We introduce the Parenthetical Terminology Translation (PTT) task, designed to mitigate potential inaccuracies by displaying the original term in parentheses alongside its translation. |
Jiyoon Myung; Jihyeon Park; Jungki Son; Kyungro Lee; Joohyung Han; | arxiv-cs.CL | 2024-10-01 |
| 87 | Disentangling Singlish Discourse Particles with Task-Driven Representation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: After disentanglement, we cluster these discourse particles to differentiate their pragmatic functions, and perform Singlish-to-English machine translation. Our work provides a computational method to understanding Singlish discourse particles, and opens avenues towards a deeper comprehension of the language and its usage. |
Linus Tze En Foo; Lynnette Hui Xian Ng; | arxiv-cs.CL | 2024-09-30 |
| 88 | Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, aligning their representations poses challenges due to the significant semantic gap between vision and text, as well as the lower quality of non-English representations caused by pre-trained encoders and data noise. To overcome these challenges, we propose LECCR, a novel solution that incorporates the multi-modal large language model (MLLM) to improve the alignment between visual and non-English representations. |
YABING WANG et. al. | arxiv-cs.CV | 2024-09-30 |
| 89 | AVIATE: Exploiting Translation Variants of Artifacts to Improve IR-based Traceability Recovery in Bilingual Software Projects Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, the translation can also bring in synonymous terms that are not consistent with those in the bilingual projects (e.g., another translation of ShuXing as property). Therefore, we propose an enhancement strategy called AVIATE that exploits translation variants from different translators by utilizing the word pairs that appear simultaneously across the translation variants from different kinds artifacts (a.k.a. consensual biterms). |
KEXIN SUN et. al. | arxiv-cs.SE | 2024-09-28 |
| 90 | Can LLMs Really Learn to Translate A Low-Resource Language from One Grammar Book? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Machine Translation from One Book (Tanzer et al., 2024) suggests prompting long-context LLMs with one grammar book enables English-Kalamang translation, an unseen XLR language – a noteworthy case of linguistic knowledge helping an NLP task. We investigate whether the book’s grammatical explanations or its parallel examples are most effective for learning XLR translation, finding almost all improvement stems from the parallel examples. |
Seth Aycock; David Stap; Di Wu; Christof Monz; Khalil Sima’an; | arxiv-cs.CL | 2024-09-27 |
| 91 | On Translating Technical Terminology: A Translation Workflow for Machine-Translated Acronyms Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The typical workflow for a professional translator to translate a document from its source language (SL) to a target language (TL) is not always focused on what many language … |
Richard Yue; John E. Ortega; Kenneth Ward Church; | arxiv-cs.CL | 2024-09-26 |
| 92 | Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We do so by introducing Direct Quality Optimization (DQO), a variant of DPO leveraging a pre-trained translation quality estimation model as a proxy for human preferences, and verify the improvements with both automatic metrics and human evaluation. |
Kaden Uhlig; Joern Wuebker; Raphael Reinauer; John DeNero; | arxiv-cs.CL | 2024-09-26 |
| 93 | Predicting Anchored Text from Translation Memories for Machine Translation Using Deep Learning Methods Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this article, we show that for a large part of those words which are anchored, we can use other techniques that are based on machine learning approaches such as Word2Vec. |
Richard Yue; John E. Ortega; | arxiv-cs.CL | 2024-09-26 |
| 94 | Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This article introduces the submission status of the Translation into Low-Resource Languages of Spain task at (WMT 2024) by Huawei Translation Service Center (HW-TSC). |
YUANCHANG LUO et. al. | arxiv-cs.CL | 2024-09-24 |
| 95 | Context-aware and Style-related Incremental Decoding Framework for Discourse-Level Literary Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This report outlines our approach for the WMT24 Discourse-Level Literary Translation Task, focusing on the Chinese-English language pair in the Constrained Track. |
YUANCHANG LUO et. al. | arxiv-cs.AI | 2024-09-24 |
| 96 | Machine Translation Advancements of Low-Resource Indian Languages By Transfer Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces the submission by Huawei Translation Center (HW-TSC) to the WMT24 Indian Languages Machine Translation (MT) Shared Task. |
BIN WEI et. al. | arxiv-cs.CL | 2024-09-24 |
| 97 | Choose The Final Translation from NMT and LLM Hypotheses Using MBR Decoding: HW-TSC’s Submission to The WMT24 General MT Shared Task Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT24 general machine translation (MT) shared task, where we participate in the English to Chinese (en2zh) language pair. |
ZHANGLIN WU et. al. | arxiv-cs.AI | 2024-09-23 |
| 98 | HW-TSC’s Submission to The CCMT 2024 Machine Translation Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents the submission of Huawei Translation Services Center (HW-TSC) to machine translation tasks of the 20th China Conference on Machine Translation (CCMT 2024). |
ZHANGLIN WU et. al. | arxiv-cs.AI | 2024-09-23 |
| 99 | Scaling Laws of Decoder-Only Models on The Multilingual Machine Translation Task Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work explores the scaling laws of decoder-only models on the multilingual and multidomain translation task. |
Gaëtan Caillaut; Raheel Qader; Mariam Nakhlé; Jingshu Liu; Jean-Gabriel Barthélemy; | arxiv-cs.CL | 2024-09-23 |
| 100 | Brotherhood at WMT 2024: Leveraging LLM-Generated Contextual Conversations for Cross-Lingual Image Captioning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe our system under the team name Brotherhood for the English-to-Lowres Multi-Modal Translation Task. |
Siddharth Betala; Ishan Chokshi; | arxiv-cs.CL | 2024-09-23 |
| 101 | RoMath: A Mathematical Reasoning Benchmark in Romanian Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper introduces RoMath, a Romanian mathematical reasoning benchmark suite comprising three datasets: RoMath-Baccalaureate, RoMath-Competitions and RoMath-Synthetic, which cover a range of mathematical domains and difficulty levels, aiming to improve non-English language models and promote multilingual AI development. |
Adrian Cosma; Ana-Maria Bucur; Emilian Radoi; | arxiv-cs.CL | 2024-09-17 |
| 102 | American Sign Language to Text Translation Using Transformer and Seq2Seq with LSTM Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study compares the Transformer with the Sequence-to-Sequence (Seq2Seq) model in translating sign language to text. |
Gregorius Guntur Sunardi Putra; Adifa Widyadhani Chanda D’Layla; Dimas Wahono; Riyanarto Sarno; Agus Tri Haryono; | arxiv-cs.CL | 2024-09-17 |
| 103 | GOSt-MT: A Knowledge Graph for Occupation-related Gender Biases in Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a novel approach to studying occupation-related gender bias through the creation of the GOSt-MT (Gender and Occupation Statistics for Machine Translation) Knowledge Graph. |
ORFEAS MENIS MASTROMICHALAKIS et. al. | arxiv-cs.CL | 2024-09-17 |
| 104 | Task Arithmetic for Language Expansion in Speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To eliminate language confusion, we propose an augmented task arithmetic method that merges an additional language control model. |
YAO-FEI CHENG et. al. | arxiv-cs.CL | 2024-09-17 |
| 105 | Translating Step-by-Step: Decomposing The Translation Process for Improved Translation Quality of Long-Form Texts Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present a step-by-step approach to long-form text translation, drawing on established processes in translation studies. |
Eleftheria Briakou; Jiaming Luo; Colin Cherry; Markus Freitag; | arxiv-cs.CL | 2024-09-10 |
| 106 | Evaluation of Google Translate for Mandarin Chinese Translation Using Sentiment and Semantic Analysis Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we provide an automated assessment of translation quality of Google Translate with human experts using sentiment and semantic analysis. |
Xuechun Wang; Rodney Beard; Rohitash Chandra; | arxiv-cs.CL | 2024-09-08 |
| 107 | Open Language Data Initiative: Advancing Low-Resource Machine Translation for Karakalpak Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study presents several contributions for the Karakalpak language: a FLORES+ devtest dataset translated to Karakalpak, parallel corpora for Uzbek-Karakalpak, Russian-Karakalpak and English-Karakalpak of 100,000 pairs each and open-sourced fine-tuned neural models for translation across these languages. |
Mukhammadsaid Mamasaidov; Abror Shopulatov; | arxiv-cs.CL | 2024-09-06 |
| 108 | Creating Domain-Specific Translation Memories for Machine Translation Fine-tuning: The TRENCARD Bilingual Cardiology Corpus Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The article introduces a semi-automatic TM preparation methodology leveraging primarily translation tools used by translators in favor of data quality and control by the translators. |
Gokhan Dogru; | arxiv-cs.CL | 2024-09-04 |
| 109 | A Data Selection Approach for Enhancing Low Resource Machine Translation Using Cross-Lingual Sentence Representations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To mitigate the impact of data quality issues, we propose a data filtering approach based on cross-lingual sentence representations. |
Nidhi Kowtal; Tejas Deshpande; Raviraj Joshi; | arxiv-cs.CL | 2024-09-04 |
| 110 | Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In addition, multilingual QA benchmarks that create datasets using machine translation have cultural differences and biases, remaining issues for use as evaluation tasks. To address these challenges, this study created an extended dataset in multiple languages without relying on machine translation. |
SHINTARO OZAKI et. al. | arxiv-cs.CL | 2024-09-02 |
| 111 | Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel approach that consists of reranking translation candidates with a classifier that distinguishes between original and translated text. |
Esther Ploeger; Huiyuan Lai; Rik van Noord; Antonio Toral; | arxiv-cs.CL | 2024-08-30 |
| 112 | From Rule-Based Models to Deep Learning Transformers Architectures for Natural Language Processing and Sign Language Translation Systems: Survey, Taxonomy and Performance Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, there are few works on sign language machine translation considering the particularity of the language being continuous and dynamic. This paper aims to address this void, providing a retrospective analysis of the temporal evolution of sign language machine translation algorithms and a taxonomy of the Transformers architectures, the most used approach in language translation. |
Nada Shahin; Leila Ismail; | arxiv-cs.AI | 2024-08-27 |
| 113 | FLEURS-ASL: Including American Sign Language in Massively Multilingual Multitask Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In order to help converge the fields, we introduce FLEURS-ASL, an extension of the multiway parallel benchmarks FLORES (for text) and FLEURS (for speech) to support their first sign language (as video), American Sign Language, translated by 5 Certified Deaf Interpreters. |
Garrett Tanzer; | arxiv-cs.CL | 2024-08-24 |
| 114 | Cultural Adaptation of Menus: A Fine-Grained Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce the ChineseMenuCSI dataset, the largest for Chinese-English menu corpora, annotated with CSI vs Non-CSI labels and a fine-grained test set. |
Zhonghe Zhang; Xiaoyu He; Vivek Iyer; Alexandra Birch; | arxiv-cs.CL | 2024-08-24 |
| 115 | Expanding FLORES+ Benchmark for More Low-Resource Settings: Portuguese-Emakhuwa Machine Translation Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present baseline results from training a Neural Machine Translation system and fine-tuning existing multilingual translation models. |
Felermino D. M. Antonio Ali; Henrique Lopes Cardoso; Rui Sousa-Silva; | arxiv-cs.CL | 2024-08-21 |
| 116 | Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce Babel-ImageNet, a massively multilingual benchmark that offers (partial) translations of ImageNet labels to 100 languages, built without machine translation or manual annotation. |
Gregor Geigle; Radu Timofte; Goran Glava�; | acl | 2024-08-20 |
| 117 | Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address key challenges facing LLMs fine-tuned for SimulMT, validate classical SimulMT concepts and practices in the context of LLMs, explore adapting LLMs that are fine-tuned for NMT to the task of SimulMT, and introduce Simul-LLM, the first open-source fine-tuning and evaluation pipeline development framework for LLMs focused on SimulMT. |
Victor Agostinelli; Max Wild; Matthew Raffel; Kazi Fuad; Lizhong Chen; | acl | 2024-08-20 |
| 118 | Document-Level Machine Translation with Large-Scale Public Parallel Corpora Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We release a large-scale open parallel corpus with document context extracted from ParaCrawl in five language pairs, along with code to compile document-level datasets for any language pair supported by ParaCrawl. We train context-aware models on these datasets and find improvements in terms of overall translation quality and targeted document-level phenomena. |
Proyag Pal; Alexandra Birch; Kenneth Heafield; | acl | 2024-08-20 |
| 119 | The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Our findings emphasize the need for fine-tuning strategies that preserve the benefits of LLMs for machine translation. |
David Stap; Eva Hasler; Bill Byrne; Christof Monz; Ke Tran; | acl | 2024-08-20 |
| 120 | Self-Modifying State Modeling for Simultaneous Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Besides, building decision paths requires unidirectional encoders to simulate streaming source inputs, which impairs the translation quality of SiMT models. To solve these issues, we propose Self-Modifying State Modeling (SM2), a novel training paradigm for SiMT task. |
Donglei Yu; Xiaomian Kang; Yuchen Liu; Yu Zhou; Chengqing Zong; | acl | 2024-08-20 |
| 121 | What Is The Best Way for ChatGPT to Translate Poetry? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite promising outcomes, our analysis reveals persistent issues in the translations generated by ChatGPT that warrant attention. To address these shortcomings, we propose an Explanation-Assisted Poetry Machine Translation (EAPMT) method, which leverages monolingual poetry explanation as a guiding information for the translation process. |
Shanshan Wang; Derek Wong; Jingming Yao; Lidia Chao; | acl | 2024-08-20 |
| 122 | Speech Sense Disambiguation: Tackling Homophone Ambiguity in End-to-End Speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To facilitate this, we first create a comprehensive homophone dictionary and an annotated dataset rich with homophone information established based on speech-text alignment. Building on this unique dictionary, we introduce AmbigST, an innovative homophone-aware contrastive learning approach that integrates a homophone-aware masking strategy. |
TENGFEI YU et. al. | acl | 2024-08-20 |
| 123 | Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Intuitively, with a growing number of seen languages the encoder sentence representation grows more flexible and easily adaptable to new languages. In this work, we test this hypothesis by zero-shot translating from unseen languages. |
Carlos Mullov; Quan Pham; Alexander Waibel; | acl | 2024-08-20 |
| 124 | Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Hence, we propose a Retrieval-Augmented Machine Translation (RAT) method which incorporates knowledge related to classical poetry for advancing the translation of Chinese Poetry in LLMs. |
ANDONG CHEN et. al. | arxiv-cs.CL | 2024-08-19 |
| 125 | Cross-Lingual Conversational Speech Summarization with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We build a baseline cascade-based system using open-source speech recognition and machine translation models. |
Max Nelson; Shannon Wotherspoon; Francis Keith; William Hartmann; Matthew Snover; | arxiv-cs.CL | 2024-08-12 |
| 126 | Simplifying Translations for Children: Iterative Simplification Considering Age of Acquisition with LLMs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we propose a method that replaces words with high Age of Acquisitions (AoA) in translations with simpler words to match the translations to the user’s level. |
Masashi Oshika; Makoto Morishita; Tsutomu Hirao; Ryohei Sasano; Koichi Takeda; | arxiv-cs.CL | 2024-08-08 |
| 127 | Evaluating The Translation Performance of Large Language Models Based on Euas-20 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite the significant progress in translation performance achieved by large language models, machine translation still faces many challenges. Therefore, in this paper, we construct the dataset Euas-20 to evaluate the performance of large language models on translation tasks, the translation ability on different languages, and the effect of pre-training data on the translation ability of LLMs for researchers and developers. |
Yan Huang; Wei Liu; | arxiv-cs.CL | 2024-08-06 |
| 128 | Conditioning LLMs with Emotion in Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a novel MT pipeline that integrates emotion information extracted from a Speech Emotion Recognition (SER) model into LLMs to enhance translation quality. |
Charles Brazier; Jean-Luc Rouas; | arxiv-cs.CL | 2024-08-06 |
| 129 | Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Intuitively, with a growing number of seen languages the encoder sentence representation grows more flexible and easily adaptable to new languages. In this work, we test this hypothesis by zero-shot translating from unseen languages. |
Carlos Mullov; Ngoc-Quan Pham; Alexander Waibel; | arxiv-cs.CL | 2024-08-05 |
| 130 | BOTS-LM: Training Large Language Models for Setswana Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we present BOTS-LM, a series of bilingual language models proficient in both Setswana and English. |
Nathan Brown; Vukosi Marivate; | arxiv-cs.CL | 2024-08-05 |
| 131 | Improving Multilingual Neural Machine Translation By Utilizing Semantic and Linguistic Features Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we propose to exploit both semantic and linguistic features between multiple languages to enhance multilingual translation. |
Mengyu Bu; Shuhao Gu; Yang Feng; | arxiv-cs.CL | 2024-08-02 |
| 132 | In-Context Example Selection Via Similarity Search Improves Low-Resource Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we focus on machine translation (MT), a task that has been shown to benefit from in-context translation examples. |
Armel Zebaze; Benoît Sagot; Rachel Bawden; | arxiv-cs.CL | 2024-08-01 |
| 133 | Encoder–Decoder Calibration for Multimodal Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The main purpose of multimodal machine translation (MMT) is to improve the quality of translation results by taking the corresponding visual context as an additional input. … |
Turghun Tayir; Lin Li; Bei Li; Jianquan Liu; Kong Aik Lee; | IEEE Transactions on Artificial Intelligence | 2024-08-01 |
| 134 | Generating Gender Alternatives in Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our key technical contribution is a novel semi-supervised solution for generating alternatives that integrates seamlessly with standard MT models and maintains high performance without requiring additional components or increasing inference overhead. |
SARTHAK GARG et. al. | arxiv-cs.CL | 2024-07-29 |
| 135 | The Power of Prompts: Evaluating and Mitigating Gender Bias in MT with LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our findings reveal pervasive gender bias across all models, with base LLMs exhibiting a higher degree of bias compared to NMT models. To combat this bias, we explore prompting engineering techniques applied to an instruction-tuned LLM. |
Aleix Sant; Carlos Escolano; Audrey Mash; Francesca De Luca Fornaciari; Maite Melero; | arxiv-cs.CL | 2024-07-26 |
| 136 | Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Gender bias has been a focal point in the study of bias in machine translation and language models. |
YIJIE CHEN et. al. | arxiv-cs.CL | 2024-07-23 |
| 137 | Machine Translation Hallucination Detection for Low and High Resource Languages Using Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper evaluates sentence-level hallucination detection approaches using Large Language Models (LLMs) and semantic similarity within massively multilingual embeddings. |
KENZA BENKIRANE et. al. | arxiv-cs.CL | 2024-07-23 |
| 138 | Fine-grained Gender Control in Machine Translation with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we tackle controlled translation in a more realistic setting of inputs with multiple entities and propose Gender-of-Entity (GoE) prompting method for LLMs. |
Minwoo Lee; Hyukhun Koh; Minsung Kim; Kyomin Jung; | arxiv-cs.CL | 2024-07-21 |
| 139 | CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: With our dataset, CoVoSwitch, spanning 13 languages, we evaluate the code-switching translation performance of two multilingual translation models, M2M-100 418M and NLLB-200 600M. |
Yeeun Kang; | arxiv-cs.CL | 2024-07-19 |
| 140 | Towards Zero-Shot Multimodal Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a method to bypass the need for fully supervised data to train MMT systems, using multimodal English data only. |
Matthieu Futeral; Cordelia Schmid; Benoît Sagot; Rachel Bawden; | arxiv-cs.CL | 2024-07-18 |
| 141 | Translate-and-Revise: Boosting Large Language Models for Constrained Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Imposing constraints on machine translation systems presents a challenging issue because these systems are not trained to make use of constraints in generating adequate, fluent translations. In this paper, we leverage the capabilities of large language models (LLMs) for constrained translation, given that LLMs can easily adapt to this task by taking translation instructions and constraints as prompts. |
PENGCHENG HUANG et. al. | arxiv-cs.CL | 2024-07-18 |
| 142 | Towards Chapter-to-Chapter Context-Aware Literary Translation Via Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Through our comprehensive analysis, we unveil that literary translation under the Ch2Ch setting is challenging in nature, with respect to both model learning methods and translation decoding algorithms. |
Linghao Jin; Li An; Xuezhe Ma; | arxiv-cs.CL | 2024-07-12 |
| 143 | Segment-Based Interactive Machine Translation for Pre-trained Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Pre-trained large language models (LLM) are starting to be widely used in many applications. In this work, we explore the use of these models in interactive machine translation (IMT) environments. |
Angel Navarro; Francisco Casacuberta; | arxiv-cs.CL | 2024-07-09 |
| 144 | An Automatic Quality Metric for Evaluating Simultaneous Interpretation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose an automatic evaluation metric for SI and SiMT focusing on word order synchronization. |
Mana Makinae; Katsuhito Sudoh; Mararu Yamada; Satoshi Nakamura; | arxiv-cs.CL | 2024-07-09 |
| 145 | Identifying Intensity of The Structure and Content in Tweets and The Discriminative Power of Attributes in Context with Referential Translation Machines Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We use referential translation machines (RTMs) to identify the similarity between an attribute and two words in English by casting the task as machine translation performance prediction (MTPP) between the words and the attribute word and the distance between their similarities for Task 10 with stacked RTM models. |
Ergun Biçici; | arxiv-cs.CL | 2024-07-06 |
| 146 | Enhancing Language Learning Through Technology: Introducing A New English-Azerbaijani (Arabic Script) Parallel Corpus Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a pioneering English-Azerbaijani (Arabic Script) parallel corpus, designed to bridge the technological gap in language learning and machine translation (MT) for under-resourced languages. |
JALIL NOURMOHAMMADI KHIARAK et. al. | arxiv-cs.CL | 2024-07-06 |
| 147 | Toucan: Many-to-Many Translation for 150 African Language Pairs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work aims to advance the field of NLP, fostering cross-cultural understanding and knowledge exchange, particularly in regions with limited language resources such as Africa. |
AbdelRahim Elmadany; Ife Adebara; Muhammad Abdul-Mageed; | arxiv-cs.CL | 2024-07-05 |
| 148 | Low Resource Twi-English Parallel Corpus for Machine Translation in Multiple Domains (Twi-2-ENG) Related Papers Related Patents Related Grants Related Venues Related Experts View |
EMMANUEL AGYEI et. al. | Discov. Comput. | 2024-07-05 |
| 149 | Finetuning End-to-End Models for Estonian Conversational Spoken Language Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We evaluated three publicly available end-to-end models: Whisper, OWSM 3.1, and SeamlessM4T. |
Tiia Sildam; Andra Velve; Tanel Alumäe; | arxiv-cs.CL | 2024-07-04 |
| 150 | A Case Study on Context-Aware Neural Machine Translation with Multi-Task Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We conduct experiments on cascade MTL architecture, which consists of one encoder and two decoders. |
Ramakrishna Appicharla; Baban Gain; Santanu Pal; Asif Ekbal; Pushpak Bhattacharyya; | arxiv-cs.CL | 2024-07-03 |
| 151 | Language Portability Strategies for Open-domain Dialogue with Pre-trained Language Models from High to Low Resource Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a study of linguistic portability strategies of large pre-trained language models (PLMs) used for open-domain dialogue systems in a high-resource language for this task. |
Ahmed Njifenjou; Virgile Sucal; Bassam Jabaian; Fabrice Lefèvre; | arxiv-cs.CL | 2024-07-01 |
| 152 | Language-agnostic Zero-Shot Machine Translation with Language-specific Modeling Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Zero-shot translation plays a key role in the multilingual Neural Machine Translation (NMT) domain, allowing multilingual systems to translate language pairs unseen in training. … |
Xiao Chen; Chirui Zhang; | 2024 International Joint Conference on Neural Networks … | 2024-06-30 |
| 153 | Towards Massive Multilingual Holistic Bias Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In the current landscape of automatic language generation, there is a need to understand, evaluate, and mitigate demographic biases as existing models are becoming increasingly multilingual. To address this, we present the initial eight languages from the MASSIVE MULTILINGUAL HOLISTICBIAS (MMHB) dataset and benchmark consisting of approximately 6 million sentences representing 13 demographic axes. |
XIAOQING ELLEN TAN et. al. | arxiv-cs.CL | 2024-06-29 |
| 154 | Less Is More: Accurate Speech Recognition & Translation Without Web-Scale Data Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We argue that state-of-the art accuracy can be reached without relying on web-scale data. |
KRISHNA C. PUVVADA et. al. | arxiv-cs.CL | 2024-06-28 |
| 155 | XTower: A Multilingual LLM for Explaining and Correcting Translation Errors Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces xTower, an open large language model (LLM) built on top of TowerBase designed to provide free-text explanations for translation errors in order to guide the generation of a corrected translation. |
MARCOS TREVISO et. al. | arxiv-cs.CL | 2024-06-27 |
| 156 | Sparse Regression for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce \textit{dice} instance selection method for proper selection of training instances, which plays an important role to learn correct feature mappings for improving the source and target coverage of the training set. |
Ergun Biçici; | arxiv-cs.CL | 2024-06-27 |
| 157 | FFN: A Fine-grained Chinese-English Financial Domain Parallel Corpus Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: For comparison, we also trained an OpenNMT model based on our dataset. We detail problems of LLMs and provide in-depth analysis, intending to stimulate further research and solutions in this largely uncharted territory. |
Yuxin Fu; Shijing Si; Leyi Mai; Xi-ang Li; | arxiv-cs.CL | 2024-06-26 |
| 158 | ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Motivated by the widespread increase in the phenomenon of code-switching between Egyptian Arabic and English in recent times, this paper explores the intricacies of machine translation (MT) and automatic speech recognition (ASR) systems, focusing on translating code-switched Egyptian Arabic-English to either English or Egyptian Arabic. Our goal is to present the methodologies employed in developing these systems, utilizing large language models such as LLama and Gemma. |
Ahmed Heakl; Youssef Zaghloul; Mennatullah Ali; Rania Hossam; Walid Gomaa; | arxiv-cs.CL | 2024-06-26 |
| 159 | Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we extend the current TIMT task and propose a novel task, **D**ocument **I**mage **M**achine **T**ranslation to **Markdown** (**DIMT2Markdown**), which aims to translate a source document image with long context and complex layout structure to markdown-formatted target translation. |
YUPU LIANG et. al. | naacl | 2024-06-20 |
| 160 | Do Multilingual Language Models Think Better in English? IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we introduce a new approach called self-translate that leverages the few-shot translation capabilities of multilingual language models. |
Julen Etxaniz; Gorka Azkune; Aitor Soroa; Oier Lacalle; Mikel Artetxe; | naacl | 2024-06-20 |
| 161 | Contextual Label Projection for Cross-Lingual Structured Prediction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce a novel label projection approach, CLaP, which translates text to the target language and performs *contextual translation* on the labels using the translated text as the context, ensuring better accuracy for the translated labels. |
Tanmay Parekh; I-Hung Hsu; Kuan-Hao Huang; Kai-Wei Chang; Nanyun Peng; | naacl | 2024-06-20 |
| 162 | M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This complexity is particularly evident in widely used PDF documents, which represent information visually. This paper addresses this gap by introducing M3T a novel benchmark dataset tailored to evaluate NMT systems on the comprehensive task of translating semi-structured documents. |
BENJAMIN HSU et. al. | naacl | 2024-06-20 |
| 163 | An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we conduct empirical studies on intra-modal and cross-modal consistency and propose two training strategies, SimRegCR and SimZeroCR, for E2E ST in regular and zero-shot scenarios. |
Pengzhi Gao; Ruiqing Zhang; Zhongjun He; Hua Wu; Haifeng Wang; | naacl | 2024-06-20 |
| 164 | Fixing Rogue Memorization in Many-to-One Multilingual Translators of Extremely-Low-Resource Languages By Rephrasing Training Samples Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we study the fine-tuning of pre-trained large high-resource language models (LLMs) into many-to-one multilingual machine translators for extremely-low-resource languages such as endangered Indigenous languages. |
Paulo Cavalin; Pedro Henrique Domingues; Claudio Pinhanez; Julio Nogima; | naacl | 2024-06-20 |
| 165 | Complexity of Symbolic Representation in Working Memory of Transformer Correlates with The Complexity of A Task Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper explores the properties of the content of symbolic working memory added to the Transformer model decoder. |
Alsu Sagirova; Mikhail Burtsev; | arxiv-cs.CL | 2024-06-20 |
| 166 | Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Surprisingly, our initial experiments found that fine-tuning with Q-LoRA for translation purposes led to performance improvements in terms of BLEU but degradation in COMET compared to in-context learning. To overcome this, we propose an alternative approach: adapting LLMs as Automatic Post-Editors (APE) rather than direct translators. |
Sai Koneru; Miriam Exel; Matthias Huck; Jan Niehues; | naacl | 2024-06-20 |
| 167 | Grammar-based Data Augmentation for Low-Resource Languages: The Case of Guarani-Spanish Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: One of the main problems low-resource languages face in NLP can be pictured as a vicious circle: data is needed to build and test tools, but the available text is scarce and there are not powerful tools to collect it. In order to break this circle for Guarani, we explore if text automatically generated from a grammar can work as a Data Augmentation technique to boost the performance of Guarani-Spanish Machine Translation (MT) systems. |
AGUST�N LUCAS et. al. | naacl | 2024-06-20 |
| 168 | How Effective Is Multi-source Pivoting for Translation of Low Resource Indian Languages? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Taking the case of English to Indian language MT, this paper explores the ‘multi-source translation’ approach with pivoting, using both source and pivot sentences to improve translation. |
Pranav Gaikwad; Meet Doshi; Raj Dabre; Pushpak Bhattacharyya; | arxiv-cs.CL | 2024-06-19 |
| 169 | Evaluating Structural Generalization in Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To address this question, we construct SGET, a machine translation dataset covering various types of compositional generalization with control of words and sentence structures. We evaluate neural machine translation models on SGET and show that they struggle more in structural generalization than in lexical generalization. |
Ryoma Kumon; Daiki Matsuoka; Hitomi Yanaka; | arxiv-cs.CL | 2024-06-19 |
| 170 | Does Context Help Mitigate Gender Bias in Neural Machine Translation? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Context-aware models have been previously suggested as a means to mitigate this type of bias. In this work, we examine this claim by analysing in detail the translation of stereotypical professions in English to German, and translation with non-informative context in Basque to Spanish. |
Harritxu Gete; Thierry Etchegoyhen; | arxiv-cs.CL | 2024-06-18 |
| 171 | Leveraging Statistical Machine Translation for Code Search Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Machine Translation (MT) has numerous applications in Software Engineering (SE). Recently, it has been employed not only for programming language translation but also as an oracle … |
Hung Phan; Ali Jannesari; | Proceedings of the 28th International Conference on … | 2024-06-18 |
| 172 | Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we get the best both worlds by integrating MT encoders directly into LLM backbones via sample-efficient self-distillation. |
Fabian David Schmidt; Philipp Borchert; Ivan Vulić; Goran Glavaš; | arxiv-cs.CL | 2024-06-18 |
| 173 | LiLiuM: EBay’s Large Language Models for E-commerce Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce the LiLiuM series of large language models (LLMs): 1B, 7B, and 13B parameter models developed 100% in-house to fit eBay’s specific needs in the e-commerce domain. |
CHRISTIAN HEROLD et. al. | arxiv-cs.CL | 2024-06-17 |
| 174 | Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce Error Span Annotation (ESA), a human evaluation protocol which combines the continuous rating of DA with the high-level error severity span marking of MQM. |
TOM KOCMI et. al. | arxiv-cs.CL | 2024-06-17 |
| 175 | CoSTA: Code-Switched Speech Translation Using Aligned Speech-Text Interleaving Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we focus on the problem of spoken translation (ST) of code-switched speech in Indian languages to English text. |
Bhavani Shankar; Preethi Jyothi; Pushpak Bhattacharyya; | arxiv-cs.CL | 2024-06-16 |
| 176 | Datasets for Multilingual Answer Sentence Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce new high-quality datasets for AS2 in five European languages (French, German, Italian, Portuguese, and Spanish), obtained through supervised Automatic Machine Translation (AMT) of existing English AS2 datasets such as ASNQ, WikiQA, and TREC-QA using a Large Language Model (LLM). |
Matteo Gabburo; Stefano Campese; Federico Agostini; Alessandro Moschitti; | arxiv-cs.CL | 2024-06-14 |
| 177 | Word Order in English-Japanese Simultaneous Interpretation: Analyses and Evaluation Using Chunk-wise Monotonic Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper analyzes the features of monotonic translations, which follow the word order of the source language, in simultaneous interpreting (SI). |
Kosuke Doi; Yuka Ko; Mana Makinae; Katsuhito Sudoh; Satoshi Nakamura; | arxiv-cs.CL | 2024-06-13 |
| 178 | Towards Multilingual Audio-Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we work towards extending Audio-Visual Question Answering (AVQA) to multilingual settings. |
ORCHID CHETIA PHUKAN et. al. | arxiv-cs.LG | 2024-06-13 |
| 179 | M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This complexity is particularly evident in widely used PDF documents, which represent information visually. This paper addresses this gap by introducing M3T, a novel benchmark dataset tailored to evaluate NMT systems on the comprehensive task of translating semi-structured documents. |
BENJAMIN HSU et. al. | arxiv-cs.CL | 2024-06-12 |
| 180 | Guiding In-Context Learning of LLMs Through Quality Estimation for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents a novel methodology for in-context learning (ICL) that relies on a search algorithm guided by domain-specific quality estimation (QE). |
Javad Pourmostafa Roshan Sharami; Dimitar Shterionov; Pieter Spronck; | arxiv-cs.CL | 2024-06-12 |
| 181 | DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation Through Dual Learning Feedback Mechanisms Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, existing self-reflection methods lack effective feedback information, limiting the translation performance. To address this, we introduce a DUAL-REFLECT framework, leveraging the dual learning of translation tasks to provide effective feedback, thereby enhancing the models’ self-reflective abilities and improving translation performance. |
ANDONG CHEN et. al. | arxiv-cs.CL | 2024-06-11 |
| 182 | Building Bridges: A Dataset for Evaluating Gender-Fair Machine Translation Into German Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We address this research gap by studying gender-fair language in English-to-German MT. Concretely, we enrich a community-created gender-fair language dictionary and sample multi-sentence test instances from encyclopedic text and parliamentary speeches. |
Manuel Lardelli; Giuseppe Attanasio; Anne Lauscher; | arxiv-cs.CL | 2024-06-10 |
| 183 | Recovering Document Annotations for Sentence-level Bitext Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we reconstruct document-level information for three (ParaCrawl, News Commentary, and Europarl) large datasets in German, French, Spanish, Italian, Polish, and Portuguese (paired with English). |
Rachel Wicks; Matt Post; Philipp Koehn; | arxiv-cs.CL | 2024-06-06 |
| 184 | StatBot.Swiss: Bilingual Open Data Exploration in Natural Language Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we release the StatBot.Swiss dataset, the first bilingual benchmark for evaluating Text-to-SQL systems based on real-world applications. |
FARHAD NOORALAHZADEH et. al. | arxiv-cs.CL | 2024-06-05 |
| 185 | What Is The Best Way for ChatGPT to Translate Poetry? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite promising outcomes, our analysis reveals persistent issues in the translations generated by ChatGPT that warrant attention. To address these shortcomings, we propose an Explanation-Assisted Poetry Machine Translation (EAPMT) method, which leverages monolingual poetry explanation as a guiding information for the translation process. |
Shanshan Wang; Derek F. Wong; Jingming Yao; Lidia S. Chao; | arxiv-cs.CL | 2024-06-05 |
| 186 | Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We find that these artifacts can significantly affect the models, confirmed by extensive experiments across diverse models, languages, and translation processes. In light of this, we present a simple data augmentation strategy that can alleviate the adverse impacts of translation artifacts. |
CHAEHUN PARK et. al. | arxiv-cs.CL | 2024-06-04 |
| 187 | How Multilingual Are Large Language Models Fine-Tuned for Translation? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: How does translation fine-tuning impact the MT capabilities of LLMs for zero-shot languages, zero-shot language pairs, and translation tasks that do not involve English? To address these questions, we conduct an extensive empirical evaluation of the translation quality of the TOWER family of language models (Alves et al., 2024) on 132 translation tasks from the multi-parallel FLORES-200 data. |
Aquia Richburg; Marine Carpuat; | arxiv-cs.CL | 2024-05-30 |
| 188 | Significance of Chain of Thought in Gender Bias Mitigation for English-Dravidian Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper examines gender bias in machine translation systems for languages such as Telugu and Kan- nada from the Dravidian family, analyzing how gender inflections affect translation accuracy and neutrality using Google Translate and Chat- GPT. |
Lavanya Prahallad; Radhika Mamidi; | arxiv-cs.CL | 2024-05-30 |
| 189 | Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a new data pruning technique: Checkpoints Across Time (CAT), that leverages early model training dynamics to identify the most relevant data points for model performance. |
EVERLYN ASIKO CHIMOTO et. al. | arxiv-cs.CL | 2024-05-29 |
| 190 | QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we address the problem of sampling a set of high-quality and diverse translations. |
GONÇALO R. A. FARIA et. al. | arxiv-cs.CL | 2024-05-28 |
| 191 | Spanish and LLM Benchmarks: Is MMLU Lost in Translation? Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The evaluation of Large Language Models (LLMs) is a key element in their continuous improvement process and many benchmarks have been developed to assess the performance of LLMs … |
IRENE PLAZA et. al. | ArXiv | 2024-05-28 |
| 192 | TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we introduce a novel model framework TransVIP that leverages diverse datasets in a cascade fashion yet facilitates end-to-end inference through joint probability. |
CHENYANG LE et. al. | arxiv-cs.CL | 2024-05-28 |
| 193 | Optimizing Example Selection for Retrieval-augmented Machine Translation with Translation Memories Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We aim to improve the upstream retrieval step and consider a fixed downstream edit-based model: the multi-Levenshtein Transformer. |
Maxime Bouthors; Josep Crego; François Yvon; | arxiv-cs.CL | 2024-05-23 |
| 194 | Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we investigate the role of translation and synthetic data in training language models. |
Sabri Boughorbel; MD Rizwan Parvez; Majd Hawasly; | arxiv-cs.CL | 2024-05-23 |
| 195 | MELD-ST: An Emotion-aware Speech Translation Dataset Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present the MELD-ST dataset for the emotion-aware speech translation task, comprising English-to-Japanese and English-to-German language pairs. |
SIROU CHEN et. al. | arxiv-cs.CL | 2024-05-21 |
| 196 | A Survey on Multi-modal Machine Translation: Tasks, Methods and Challenges Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we begin by offering an exhaustive overview of 99 prior works, comprehensively summarizing representative studies from the perspectives of dominant models, datasets, and evaluation metrics. |
HUANGJUN SHEN et. al. | arxiv-cs.CL | 2024-05-21 |
| 197 | DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we introduce DiffNorm, a diffusion-based normalization strategy that simplifies data distributions for training NAT models. |
Weiting Tan; Jingyu Zhang; Lingfeng Shen; Daniel Khashabi; Philipp Koehn; | arxiv-cs.CL | 2024-05-21 |
| 198 | Beyond MLE: Investigating SEARNN for Low-Resourced Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: With an average BLEU score improvement of $5.4$\% over the MLE objective, we proved that SEARNN is indeed a viable algorithm to effectively train RNNs on machine translation for low-resourced languages. |
Chris Emezue; | arxiv-cs.CL | 2024-05-20 |
| 199 | Neural Machine Translation for Low-Resource Languages from A Chinese-centric Perspective: A Survey Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Machine translation–the automatic transformation of one natural language (source language) into another (target language) through computational means–occupies a central role in … |
JINYI ZHANG et. al. | ACM Transactions on Asian and Low-Resource Language … | 2024-05-16 |
| 200 | Enhancing Gender-Inclusive Machine Translation with Neomorphemes and Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Accordingly, they still fall short in using gender-inclusive language, also representative of non-binary identities. In this paper, we look at gender-inclusive neomorphemes, neologistic elements that avoid binary gender markings as an approach towards fairer MT. In this direction, we explore prompting techniques with large language models (LLMs) to translate from English into Italian using neomorphemes. |
Andrea Piergentili; Beatrice Savoldi; Matteo Negri; Luisa Bentivogli; | arxiv-cs.CL | 2024-05-14 |
| 201 | LLM-Assisted Rule Based Machine Translation for Low/No-Resource Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new paradigm for machine translation that is particularly useful for no-resource languages (those without any publicly available bilingual or monolingual corpora): LLM-RBMT (LLM-Assisted Rule Based Machine Translation). |
Jared Coleman; Bhaskar Krishnamachari; Khalil Iskarous; Ruben Rosales; | arxiv-cs.CL | 2024-05-14 |
| 202 | An Empirical Study on The Robustness of Massively Multilingual Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we empirically investigate the translation robustness of Indonesian-Chinese translation in the face of various naturally occurring noise. |
Leiyu Pan; Deyi Xiong; | arxiv-cs.CL | 2024-05-13 |
| 203 | CANTONMT: Investigating Back-Translation and Model-Switch Mechanisms for Cantonese-English Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper investigates the development and evaluation of machine translation models from Cantonese to English, where we propose a novel approach to tackle low-resource language translations. |
Kung Yin Hong; Lifeng Han; Riza Batista-Navarro; Goran Nenadic; | arxiv-cs.CL | 2024-05-13 |
| 204 | Fairness Testing of Machine Translation Systems Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Machine translation is integral to international communication and extensively employed in diverse human-related applications. Despite remarkable progress, fairness issues persist … |
Zeyu Sun; Zhenpeng Chen; Jie M. Zhang; Dan Hao; | ACM Transactions on Software Engineering and Methodology | 2024-05-09 |
| 205 | Using Machine Translation to Augment Multilingual Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we explore the effects of using machine translation to fine-tune a multilingual model for a classification task across multiple languages. |
Adam King; | arxiv-cs.CL | 2024-05-08 |
| 206 | Relay Decoding: Concatenating Large Language Models for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: When it is challenging to find large models that support the desired languages, resorting to continuous learning methods becomes a costly endeavor. To mitigate these expenses, we propose an innovative approach called RD (Relay Decoding), which entails concatenating two distinct large models that individually support the source and target languages. |
CHENGPENG FU et. al. | arxiv-cs.CL | 2024-05-05 |
| 207 | Sentiment Analysis Across Languages: Evaluation Before and After Machine Translation to English Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper examines the performance of transformer models in Sentiment Analysis tasks across multilingual datasets and text that has undergone machine translation. |
Aekansh Kathunia; Mohammad Kaif; Nalin Arora; N Narotam; | arxiv-cs.CL | 2024-05-05 |
| 208 | The IgboAPI Dataset: Empowering Igbo Language Technologies Through Multi-dialectal Enrichment Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In response, we present the IgboAPI dataset, a multi-dialectal Igbo-English dictionary dataset, developed with the aim of enhancing the representation of Igbo dialects. |
CHRIS CHINENYE EMEZUE et. al. | arxiv-cs.CL | 2024-05-02 |
| 209 | E-learning Application in English Writing Classroom Based on Neural Machine Translation and Semantic Analysis Algorithms Related Papers Related Patents Related Grants Related Venues Related Experts View |
Yaqiu Wang; | Entertain. Comput. | 2024-05-01 |
| 210 | Context-Aware Machine Translation with Source Coreference Explanation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This can lead to the explain-away effect, wherein the models only consider features easier to explain predictions, resulting in inaccurate translations. To address this issue, we propose a model that explains the decisions made for translation by predicting coreference features in the input. |
Huy Hien Vu; Hidetaka Kamigaito; Taro Watanabe; | arxiv-cs.CL | 2024-04-30 |
| 211 | Suvach — Generated Hindi QA Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a new benchmark specifically designed for evaluating Hindi EQA models and discusses the methodology to do the same for any task. |
Vaishak Narayanan; Prabin Raj KP; Saifudheen Nouphal; | arxiv-cs.CL | 2024-04-30 |
| 212 | 3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Abstract: Multimodal machine translation (MMT) is a challenging task that seeks to improve translation quality by incorporating visual information. However, recent studies have indicated … |
XINYU MA et. al. | International Conference on Language Resources and … | 2024-04-29 |
| 213 | Quality Estimation with $k$-nearest Neighbors and Automatic Evaluation for Model-specific Quality Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a model-specific, unsupervised QE approach, termed $k$NN-QE, that extracts information from the MT model’s training data using $k$-nearest neighbors. |
Tu Anh Dinh; Tobias Palzer; Jan Niehues; | arxiv-cs.CL | 2024-04-27 |
| 214 | Translation of Multifaceted Data Without Re-Training of Machine Translation Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, we argue that this practice often overlooks the interrelation between components within the same data point. To address this limitation, we propose a novel MT pipeline that considers the intra-data relation in implementing MT for training data. |
HYEONSEOK MOON et. al. | arxiv-cs.CL | 2024-04-24 |
| 215 | Setting Up The Data Printer with Improved English to Ukrainian Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Examples of task performance expressed in English are abundant, so with a high-quality translation system our community will be enabled to curate datasets faster. To aid this goal, we introduce a recipe to build a translation system using supervised finetuning of a large pretrained language model with a noisy parallel dataset of 3M pairs of Ukrainian and English sentences followed by a second phase of training using 17K examples selected by k-fold perplexity filtering on another dataset of higher quality. |
Yurii Paniv; Dmytro Chaplynskyi; Nikita Trynus; Volodymyr Kyrylov; | arxiv-cs.CL | 2024-04-23 |
| 216 | Automated Multi-Language to English Machine Translation Using Generative Pre-Trained Transformers Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we examine using local Generative Pretrained Transformer (GPT) models to perform automated zero shot black-box, sentence wise, multi-natural-language translation into English text. |
Elijah Pelofske; Vincent Urias; Lorie M. Liebrock; | arxiv-cs.CL | 2024-04-22 |
| 217 | From LLM to NMT: Advancing Low-Resource Machine Translation with Claude IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show that Claude 3 Opus, a large language model (LLM) released by Anthropic in March 2024, exhibits stronger machine translation competence than other LLMs. |
Maxim Enis; Mark Hopkins; | arxiv-cs.CL | 2024-04-21 |
| 218 | Vector Quantization Knowledge Transfer for End-to-End Text Image Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: End-to-end text image machine translation (TIMT) aims at translating source language embedded in images into target language without recognizing intermediate texts in images. … |
Cong Ma; Yaping Zhang; Yang Zhao; Yu Zhou; Chengqing Zong; | ICASSP 2024 – 2024 IEEE International Conference on … | 2024-04-14 |
| 219 | Multilingual Evaluation of Semantic Textual Relatedness Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work aims to not only showcase our achievements but also inspire further research in multilingual STR, particularly for low-resourced languages. |
SHARVI ENDAIT et. al. | arxiv-cs.CL | 2024-04-13 |
| 220 | Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian As A Case Study Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we revisit state-of-the-art Neural Machine Translation techniques to develop automatic translation systems between German and Bavarian. |
Wan-Hua Her; Udo Kruschwitz; | arxiv-cs.CL | 2024-04-12 |
| 221 | Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Machine Translation (MT) remains one of the last NLP tasks where large language models (LLMs) have not yet replaced dedicated supervised systems. This work exploits the complementary strengths of LLMs and supervised MT by guiding LLMs to automatically post-edit MT with external feedback on its quality, derived from Multidimensional Quality Metric (MQM) annotations. |
Dayeon Ki; Marine Carpuat; | arxiv-cs.CL | 2024-04-11 |
| 222 | Exploring The Necessity of Visual Modality in Multimodal Machine Translation Using Authentic Datasets Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we adhere to the universal multimodal machine translation framework proposed by Tang et al. (2022). |
ZI LONG et. al. | arxiv-cs.CL | 2024-04-09 |
| 223 | Low-Resource Machine Translation Through Retrieval-Augmented LLM Prompting: A Study on The Mambai Language Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This study explores the use of large language models (LLMs) for translating English into Mambai, a low-resource Austronesian language spoken in Timor-Leste, with approximately 200,000 native speakers. |
Raphaël Merx; Aso Mahmudi; Katrina Langford; Leo Alberto de Araujo; Ekaterina Vylomova; | arxiv-cs.CL | 2024-04-07 |
| 224 | MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness (STR), on Track C: Cross-lingual. |
Shijia Zhou; Huangyan Shan; Barbara Plank; Robert Litschko; | arxiv-cs.CL | 2024-04-03 |
| 225 | Towards Better Understanding of Cybercrime: The Role of Fine-Tuned LLMs in Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose using fine-tuned Large Language Models (LLM) to generate translations that can accurately capture the nuances of cybercrime language. |
Veronica Valeros; Anna Širokova; Carlos Catania; Sebastian Garcia; | arxiv-cs.CL | 2024-04-02 |
| 226 | Low-resource Neural Machine Translation with Morphological Modeling Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a framework-solution for modeling complex morphology in low-resource settings. |
Antoine Nzeyimana; | arxiv-cs.CL | 2024-04-02 |
| 227 | Improving Vietnamese-English Medical Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce MedEV — a high-quality Vietnamese-English parallel dataset constructed specifically for the medical domain, comprising approximately 360K sentence pairs. |
Nhu Vo; Dat Quoc Nguyen; Dung D. Le; Massimo Piccardi; Wray Buntine; | arxiv-cs.CL | 2024-03-28 |
| 228 | A Tulu Resource for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present the first parallel dataset for English-Tulu translation. |
Manu Narayanan; Noëmi Aepli; | arxiv-cs.CL | 2024-03-28 |
| 229 | KazParC: Kazakh Parallel Corpus for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce KazParC, a parallel corpus designed for machine translation across Kazakh, English, Russian, and Turkish. |
Rustem Yeshpanov; Alina Polonskaya; Huseyin Atakan Varol; | arxiv-cs.CL | 2024-03-28 |
| 230 | Going Beyond Word Matching: Syntax Improves In-context Example Selection for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a syntax-based in-context example selection method for MT, by computing the syntactic similarity between dependency trees using Polynomial Distance. |
Chenming Tang; Zhixiang Wang; Yunfang Wu; | arxiv-cs.CL | 2024-03-28 |
| 231 | M3P: Towards Multimodal Multilingual Translation with Multimodal Prompt Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a framework to leverage the multimodal prompt to guide the Multimodal Multilingual neural Machine Translation (m3P), which aligns the representations of different languages with the same meaning and generates the conditional vision-language memory for translation. |
JIAN YANG et. al. | arxiv-cs.CL | 2024-03-26 |
| 232 | The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Theoretically, however, the method should not work in general. We therefore conduct controlled experiments with artificial languages to determine what properties of languages make back-translation an effective training method, covering lexical, syntactic, and semantic properties. |
Nicolas Guerin; Shane Steinert-Threlkeld; Emmanuel Chemla; | arxiv-cs.CL | 2024-03-26 |
| 233 | Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we tackle the problem of code-mixed (Hinglish and Bengalish) to English machine translation. |
Kartik Kartik; Sanjana Soni; Anoop Kunchukuttan; Tanmoy Chakraborty; Md Shad Akhtar; | arxiv-cs.CL | 2024-03-25 |
| 234 | Prediction of Translation Techniques for The Translation Process Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In contrast, the process of human-generated translation relies on a wide range of translation techniques, which are crucial for ensuring linguistic adequacy and fluency. This study suggests that these translation techniques could further optimize machine translation if they are automatically identified before being applied to guide the translation process effectively. |
Fan Zhou; Vincent Vandeghinste; | arxiv-cs.CL | 2024-03-21 |
| 235 | Multi-Dimensional Machine Translation Evaluation: Model Evaluation and Resource for Korean Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Previous studies have demonstrated the feasibility of MQM annotation but there are, to our knowledge, no computational models that predict MQM scores for novel texts, due to a lack of resources. In this paper, we address these shortcomings by (a) providing a 1200-sentence MQM evaluation benchmark for the language pair English-Korean and (b) reframing MT evaluation as the multi-task problem of simultaneously predicting several MQM scores using SOTA language models, both in a reference-based MT evaluation setup and a reference-free quality estimation (QE) setup. |
Dojun Park; Sebastian Padó; | arxiv-cs.CL | 2024-03-19 |
| 236 | Enhancing Taiwanese Hokkien Dual Translation By Exploring and Standardizing of Four Writing Systems Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Machine translation focuses mainly on high-resource languages (HRLs), while low-resource languages (LRLs) like Taiwanese Hokkien are relatively under-explored. The study aims to address this gap by developing a dual translation model between Taiwanese Hokkien and both Traditional Mandarin Chinese and English. |
Bo-Han Lu; Yi-Hsuan Lin; En-Shiun Annie Lee; Richard Tzong-Han Tsai; | arxiv-cs.CL | 2024-03-18 |
| 237 | CantonMT: Cantonese to English NMT Platform with Fine-Tuned Models Using Synthetic Back-Translation Data Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we deploy a standard data augmentation methodology by back-translation to a new language translation direction Cantonese-to-English. |
Kung Yin Hong; Lifeng Han; Riza Batista-Navarro; Goran Nenadic; | arxiv-cs.CL | 2024-03-17 |
| 238 | CantonMT: Cantonese to English NMT Platform with Fine-Tuned Models Using Real and Synthetic Back-Translation Data Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Neural Machine Translation (NMT) for low-resource languages remains a challenge for many NLP researchers. In this work, we deploy a standard data augmentation methodology by … |
Kung Yin Hong; Lifeng Han; R. Batista-Navarro; Goran Nenadic; | ArXiv | 2024-03-17 |
| 239 | A Novel Paradigm Boosting Translation Capabilities of Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. |
JIAXIN GUO et. al. | arxiv-cs.CL | 2024-03-17 |
| 240 | To Label or Not to Label: Hybrid Active Learning for Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Both approaches have limitations – diversity methods may extract varied but trivial examples, while uncertainty sampling can yield repetitive, uninformative instances. To bridge this gap, we propose Hybrid Uncertainty and Diversity Sampling (HUDS), an AL strategy for domain adaptation in NMT that combines uncertainty and diversity for sentence selection. |
Abdul Hameed Azeemi; Ihsan Ayyub Qazi; Agha Ali Raza; | arxiv-cs.CL | 2024-03-14 |
| 241 | Scaling Behavior of Machine Translation with Large Language Models Under Prompt Injection Attacks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Their generality, however, opens them up to subversion by end users who may embed into their requests instructions that cause the model to behave in unauthorized and possibly unsafe ways. In this work we study these Prompt Injection Attacks (PIAs) on multiple families of LLMs on a Machine Translation task, focusing on the effects of model size on the attack success rates. |
Zhifan Sun; Antonio Valerio Miceli-Barone; | arxiv-cs.CL | 2024-03-14 |
| 242 | ACT-MNMT Auto-Constriction Turning for Multilingual Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, due to the mixture of multilingual data during the pre-training of LLM, the LLM-based translation models face the off-target issue in both prompt-based methods, including a series of phenomena, namely instruction misunderstanding, translation with wrong language and over-generation. For this issue, this paper introduces an \textbf{\underline{A}}uto-\textbf{\underline{C}}onstriction \textbf{\underline{T}}urning mechanism for \textbf{\underline{M}}ultilingual \textbf{\underline{N}}eural \textbf{\underline{M}}achine \textbf{\underline{T}}ranslation (\model), which is a novel supervised fine-tuning mechanism and orthogonal to the traditional prompt-based methods. |
Shaojie Dai; Xin Liu; Ping Luo; Yue Yu; | arxiv-cs.CL | 2024-03-11 |
| 243 | Consensus-Based Machine Translation for Code-Mixed Texts Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Multilingualism in India is widespread due to its long history of foreign acquaintances. This leads to the presence of an audience familiar with conversing using more than one … |
S. Mahata; Dipankar Das; Sivaji Bandyopadhyay; | ACM Transactions on Asian and Low-Resource Language … | 2024-03-09 |
| 244 | Enhanced Auto Language Prediction with Dictionary Capsule — A Novel Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The paper presents a novel Auto Language Prediction Dictionary Capsule (ALPDC) framework for language prediction and machine translation. |
PINNI VENKATA ABHIRAM et. al. | arxiv-cs.CL | 2024-03-09 |
| 245 | Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we directly compared two data augmentation techniques as potential solutions for monolingual STS: (a) cross-lingual transfer that exploits English resources alone as training data to yield non-English sentence embeddings as zero-shot inference, and (b) machine translation that coverts English data into pseudo non-English training data in advance. |
Sho Hoshino; Akihiko Kato; Soichiro Murakami; Peinan Zhang; | arxiv-cs.CL | 2024-03-08 |
| 246 | Attempt Towards Stress Transfer in Speech-to-Speech Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an Indian English-to-Hindi SSMT system that can transfer stress and aim to enhance the overall quality and engagement of educational content. |
Sai Akarsh; Vamshi Raghusimha; Anindita Mondal; Anil Vuppala; | arxiv-cs.CL | 2024-03-06 |
| 247 | BiVert: Bidirectional Vocabulary Evaluation Using Relations for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a bidirectional semantic-based evaluation method designed to assess the sense distance of the translation from the source text. |
Carinne Cherf; Yuval Pinter; | arxiv-cs.CL | 2024-03-06 |
| 248 | GaHealth: An English-Irish Bilingual Corpus of Health Data Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Our study outlines the process used in developing the corpus and empirically demonstrates the benefits of using an in-domain dataset for the health domain. |
Séamus Lankford; Haithem Afli; Órla Ní Loinsigh; Andy Way; | arxiv-cs.CL | 2024-03-06 |
| 249 | General2Specialized LLMs Translation for E-commerce Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Taking e-commerce as an example, the texts usually include amounts of domain-related words and have more grammar problems, which leads to inferior performances of current NMT methods. To address these problems, we collect two domain-related resources, including a set of term pairs (aligned Chinese-English bilingual terms) and a parallel corpus annotated for the e-commerce domain. |
KAIDI CHEN et. al. | arxiv-cs.CL | 2024-03-06 |
| 250 | GaHealth: An English–Irish Bilingual Corpus of Health Data Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Machine Translation is a mature technology for many high-resource language pairs. However in the context of low-resource languages, there is a paucity of parallel data datasets … |
Séamus Lankford; Haithem Afli; Orla Ni Loinsigh; Andy Way; | ArXiv | 2024-03-06 |
| 251 | Detecting Concrete Visual Tokens for Multimodal Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce new methods for detection of visually and contextually relevant (concrete) tokens from source sentences, including detection with natural language processing (NLP), detection with object detection, and a joint detection-verification technique. |
Braeden Bowen; Vipin Vijayan; Scott Grigsby; Timothy Anderson; Jeremy Gwinnup; | arxiv-cs.CL | 2024-03-05 |
| 252 | Adding Multimodal Capabilities to A Text-only Translation Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In order to perform well on both Multi30k and typical text-only datasets, we use a performant text-only machine translation (MT) model as the starting point of our MMT model. |
Vipin Vijayan; Braeden Bowen; Scott Grigsby; Timothy Anderson; Jeremy Gwinnup; | arxiv-cs.CL | 2024-03-05 |
| 253 | The Case for Evaluating Multimodal Translation Models on Text Datasets Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Namely, the use of visual information by the MMT model cannot be shown directly from the Multi30k test set results and the sentences in Multi30k are are image captions, i.e., short, descriptive sentences, as opposed to complex sentences that typical text-only machine translation models are evaluated against. Therefore, we propose that MMT models be evaluated using 1) the CoMMuTE evaluation framework, which measures the use of visual information by MMT models, 2) the text-only WMT news translation task test sets, which evaluates translation performance against complex sentences, and 3) the Multi30k test sets, for measuring MMT model performance against a real MMT dataset. |
Vipin Vijayan; Braeden Bowen; Scott Grigsby; Timothy Anderson; Jeremy Gwinnup; | arxiv-cs.CL | 2024-03-05 |
| 254 | Transformers for Low-Resource Languages: Is Féidir Linn! IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The Transformer model is the state-of-the-art in Machine Translation. However and in general and neural translation models often under perform on language pairs with insufficient … |
Séamus Lankford; H. Alfi; Andy Way; | Machine Translation Summit | 2024-03-04 |
| 255 | Machine Translation in The Covid Domain: An English-Irish Case Study for LoResMT 2021 IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Translation models for the specific domain of translating Covid data from English to Irish were developed for the LoResMT 2021 shared task. |
Séamus Lankford; Haithem Afli; Andy Way; | arxiv-cs.CL | 2024-03-02 |
| 256 | EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our work, we observe that both direct and pivot translations are noisy and achieve less satisfactory performance. We propose EBBS, an ensemble method with a novel bi-level beam search algorithm, where each ensemble component explores its own prediction step by step at the lower level but they are synchronized by a soft voting mechanism at the upper level. |
Yuqiao Wen; Behzad Shayegh; Chenyang Huang; Yanshuai Cao; Lili Mou; | arxiv-cs.CL | 2024-02-29 |
| 257 | A Multitask Co-training Framework for Improving Speech Translation By Leveraging Speech Recognition and Machine Translation Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View |
Yue Zhou; Yuxuan Yuan; Xiaodong Shi; | Neural Comput. Appl. | 2024-02-27 |
| 258 | An Interpretable Error Correction Method for Enhancing Code-to-code Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, researchers frequently invest substantial time and computational resources in retraining models, yet the improvement in translation accuracy is quite limited. To address these issues, we introduce a novel approach, $k\text{NN-ECD}$, which combines $k$-nearest-neighbor search with a key-value error correction datastore to overwrite the wrong translations of TransCoder-ST. |
Min Xue; Artur Andrzejak; Marla Leuther; | iclr | 2024-02-26 |
| 259 | MT-Ranker: Reference-free Machine Translation Evaluation By Inter-system Ranking Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we formulate the reference-free MT evaluation into a pairwise ranking problem. |
Ibraheem Muhammad Moosa; Rui Zhang; Wenpeng Yin; | iclr | 2024-02-26 |
| 260 | A Benchmark for Learning to Translate A New Language from One Grammar Book IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We turn to a field that is explicitly motivated and bottlenecked by a scarcity of web data: low-resource languages. In this paper, we introduce MTOB (Machine Translation from One Book), a benchmark for learning to translate between English and Kalamang—a language with less than 200 speakers and therefore virtually no presence on the web—using several hundred pages of field linguistics reference materials. |
Garrett Tanzer; Mirac Suzgun; Eline Visser; Dan Jurafsky; Luke Melas-Kyriazi; | iclr | 2024-02-26 |
| 261 | TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Importantly, feeding back such error information into the LLMs can lead to self-refinement and result in improved translation performance. Motivated by these insights, we introduce a systematic LLM-based self-refinement translation framework, named \textbf{TEaR}, which stands for \textbf{T}ranslate, \textbf{E}stimate, \textbf{a}nd \textbf{R}efine, marking a significant step forward in this direction. |
ZHAOPENG FENG et. al. | arxiv-cs.CL | 2024-02-26 |
| 262 | A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we propose a novel fine-tuning approach for LLMs that is specifically designed for the translation task, eliminating the need for the abundant parallel data that traditional translation models usually depend on. |
Haoran Xu; Young Jin Kim; Amr Sharaf; Hany Hassan Awadalla; | iclr | 2024-02-26 |
| 263 | TMT: Tri-Modal Translation Between Speech, Image, and Text By Processing Different Modalities As Different Languages Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose a novel Tri-Modal Translation (TMT) model that translates between arbitrary modalities spanning speech, image, and text. |
MINSU KIM et. al. | arxiv-cs.CL | 2024-02-25 |
| 264 | Direct Punjabi to English Speech Translation Using Discrete Units Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: With a motive to contribute towards speech translation research for low-resource languages, our work presents a direct speech-to-speech translation model for one of the Indic languages called Punjabi to English. |
Prabhjot Kaur; L. Andrew M. Bush; Weisong Shi; | arxiv-cs.CL | 2024-02-24 |
| 265 | Could We Have Had Better Multilingual LLMs If English Was Not The Central Language? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Large Language Models (LLMs) demonstrate strong machine translation capabilities on languages they are trained on. |
Ryandito Diandaru; Lucky Susanto; Zilu Tang; Ayu Purwarianti; Derry Wijaya; | arxiv-cs.CL | 2024-02-21 |
| 266 | GATE X-E : A Challenge Set for Gender-Fair Translations from Weakly-Gendered Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite numerous studies on gender bias in translations into English from weakly gendered-languages, there are no benchmarks for evaluating this phenomenon or for assessing mitigation strategies. To address this gap, we introduce GATE X-E, an extension to the GATE (Rarrick et al., 2023) corpus, that consists of human translations from Turkish, Hungarian, Finnish, and Persian into English. |
Spencer Rarrick; Ranjita Naik; Sundar Poudel; Vishal Chowdhary; | arxiv-cs.CL | 2024-02-21 |
| 267 | Bangla AI: A Framework for Machine Translation Utilizing Large Language Models for Ethnic Media Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The paper outlines a theoretical framework elucidating the integration of LLM and MMT into the news searching and translation processes for ethnic media. |
MD Ashraful Goni; Fahad Mostafa; Kerk F. Kee; | arxiv-cs.CL | 2024-02-21 |
| 268 | SiLLM: Large Language Models for Simultaneous Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose SiLLM, which delegates the two sub-tasks to separate agents, thereby incorporating LLM into SiMT. |
Shoutao Guo; Shaolei Zhang; Zhengrui Ma; Min Zhang; Yang Feng; | arxiv-cs.CL | 2024-02-20 |
| 269 | UMBCLU at SemEval-2024 Task 1A and 1C: Semantic Textual Relatedness with and Without Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Large language models (LLMs) have shown impressive performance on several natural language understanding tasks such as multilingual machine translation (MMT), semantic similarity (STS), and encoding sentence embeddings. Using a combination of LLMs that perform well on these tasks, we developed two STR models, $\textit{TranSem}$ and $\textit{FineSem}$, for the supervised and cross-lingual settings. |
Shubhashis Roy Dipta; Sai Vallurupalli; | arxiv-cs.CL | 2024-02-20 |
| 270 | UMBCLU at SemEval-2024 Task 1: Semantic Textual Relatedness with and Without Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The aim of SemEval-2024 Task 1, “Semantic Textual Relatedness for African and Asian Languages” is to develop models for identifying semantic textual relatedness (STR) between two … |
Shubhashis Roy Dipta; Sai Vallurupalli; | Proceedings of the 18th International Workshop on Semantic … | 2024-02-20 |
| 271 | Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we explore leveraging reinforcement learning with human feedback (\textit{RLHF}) to improve translation quality. |
NUO XU et. al. | arxiv-cs.CL | 2024-02-18 |
| 272 | Rethinking Human-like Translation Strategy: Integrating Drift-Diffusion Model with Large Language Models for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, prior work on LLM-based machine translation has mainly focused on better utilizing training data, demonstrations, or pre-defined and universal knowledge to improve performance, with a lack of consideration of decision-making like human translators. In this paper, we incorporate Thinker with the Drift-Diffusion Model (Thinker-DDM) to address this issue. |
HONGBIN NA et. al. | arxiv-cs.CL | 2024-02-16 |
| 273 | A Study for Enhancing Low-resource Thai-Myanmar-English Neural Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Several methodologies have recently been proposed to enhance the performance of low-resource Neural Machine Translation (NMT). However, these techniques have yet to be explored … |
Mya Ei San; Sasiporn Usanavasin; Ye Kyaw Thu; Manabu Okumura; | ACM Transactions on Asian and Low-Resource Language … | 2024-02-13 |
| 274 | Unsupervised Sign Language Translation and Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a sliding window method to address the issues of aligning variable-length text with video sequences. |
ZHENGSHENG GUO et. al. | arxiv-cs.CL | 2024-02-12 |
| 275 | A Prompt Response to The Demand for Automatic Gender-Neutral Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: For such a scenario, large language models offer hitherto unforeseen possibilities, as they come with the distinct advantage of being versatile in various (sub)tasks when provided with explicit instructions. In this paper, we explore this potential to automate GNT by comparing MT with the popular GPT-4 model. |
Beatrice Savoldi; Andrea Piergentili; Dennis Fucci; Matteo Negri; Luisa Bentivogli; | arxiv-cs.CL | 2024-02-08 |
| 276 | TransLLaMa: LLM-based Simultaneous Translation System IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This study demonstrates that, after fine-tuning on a small dataset comprising causally aligned source and target sentence pairs, a pre-trained open-source LLM can control input segmentation directly by generating a special wait token. |
Roman Koshkin; Katsuhito Sudoh; Satoshi Nakamura; | arxiv-cs.CL | 2024-02-07 |
| 277 | Error Analysis of Pretrained Language Models (PLMs) in English-to-Arabic Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View |
H. Al-Khalifa; Khaloud Al-Khalefah; Hesham Haroon; | Hum. Centric Intell. Syst. | 2024-02-05 |
| 278 | A Morphologically-Aware Dictionary-based Data Augmentation Technique for Machine Translation of Under-Represented Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose strategies to synthesize parallel data relying on morpho-syntactic information and using bilingual lexicons along with a small amount of seed parallel data. |
Md Mahfuz Ibn Alam; Sina Ahmadi; Antonios Anastasopoulos; | arxiv-cs.CL | 2024-02-02 |
| 279 | Neural Machine Translation for Malayalam Paraphrase Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study explores four methods of generating paraphrases in Malayalam, utilizing resources available for English paraphrasing and pre-trained Neural Machine Translation (NMT) models. |
Christeena Varghese; Sergey Koshelev; Ivan P. Yamshchikov; | arxiv-cs.CL | 2024-01-31 |
| 280 | Massively Multilingual Text Translation For Low-Resource Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We attempt to leverage translation resources from rich-resource languages to efficiently produce best possible translation quality for well known texts, which are available in multiple languages, in a new, low-resource language. |
Zhong Zhou; | arxiv-cs.CL | 2024-01-29 |
| 281 | MultiMUC: Multilingual Template Filling on MUC-4 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce MultiMUC, the first multilingual parallel corpus for template filling, comprising translations of the classic MUC-4 template filling benchmark into five languages: Arabic, Chinese, Farsi, Korean, and Russian. |
WILLIAM GANTT et. al. | arxiv-cs.CL | 2024-01-29 |
| 282 | Misgendering and Assuming Gender in Machine Translation When Working with Low-Resource Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This chapter focuses on gender-related errors in machine translation (MT) in the context of low-resource languages. |
Sourojit Ghosh; Srishti Chatterjee; | arxiv-cs.CL | 2024-01-23 |
| 283 | How Far Can 100 Samples Go? Unlocking Overall Zero-Shot Multilingual Translation Via Tiny Multi-Parallel Data Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we show that for an English-centric model, surprisingly large zero-shot improvements can be achieved by simply fine-tuning with a very small amount of multi-parallel data. |
Di Wu; Shaomu Tan; Yan Meng; David Stap; Christof Monz; | arxiv-cs.CL | 2024-01-22 |
| 284 | An Empirical Study of In-context Learning in LLMs for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Recent interest has surged in employing Large Language Models (LLMs) for machine translation (MT) via in-context learning (ICL) (Vilar et al., 2023). |
Pranjal A. Chitale; Jay Gala; Raj Dabre; | arxiv-cs.CL | 2024-01-22 |
| 285 | Gender Bias in Machine Translation and The Era of Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This chapter examines the role of Machine Translation in perpetuating gender bias, highlighting the challenges posed by cross-linguistic settings and statistical dependencies. |
Eva Vanmassenhove; | arxiv-cs.CL | 2024-01-18 |
| 286 | Gradable ChatGPT Translation Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Accordingly, this paper proposes a generic taxonomy, which defines gradable translation prompts in terms of expression type, translation style, POS information and explicit statement, thus facilitating the construction of prompts endowed with distinct attributes tailored for various translation tasks. |
Hui Jiao; Bei Peng; Lu Zong; Xiaojun Zhang; Xinwei Li; | arxiv-cs.CL | 2024-01-18 |
| 287 | Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directions Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Generative large language models (LLMs) have demonstrated exceptional proficiency in various natural language processing (NLP) tasks, including machine translation, question … |
Nooshin Pourkamali; Shler Ebrahim Sharifi; | ArXiv | 2024-01-16 |
| 288 | A Novel Approach for Automatic Program Repair Using Round-Trip Translation with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper proposes bypassing the fine-tuning step and using Round-Trip Translation (RTT): translation of code from one programming language to another programming or natural language, and back. |
Fernando Vallecillos Ruiz; Anastasiia Grishina; Max Hort; Leon Moonen; | arxiv-cs.SE | 2024-01-15 |
| 289 | Enhancing Document-level Translation of Large Language Model Via Translation Mixed-instructions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the issue, we propose an approach that combines sentence-level and document-level translation instructions of varying lengths to fine-tune LLMs. |
Yachao Li; Junhui Li; Jing Jiang; Min Zhang; | arxiv-cs.CL | 2024-01-15 |
| 290 | An Approach for Mistranslation Removal from Popular Dataset for Indic MT Task Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Hence, the MT systems built using this dataset cannot perform to their usual potential. In this paper, we propose an algorithm to remove mistranslations from the training corpus and evaluate its performance and efficiency. |
Sudhansu Bala Das; Leo Raphael Rodrigues; Tapas Kumar Mishra; Bidyut Kr. Patra; | arxiv-cs.CL | 2024-01-12 |
| 291 | Adapting Large Language Models for Document-Level Machine Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our results show that specialized models can sometimes surpass GPT-4 in translation performance but still face issues like off-target translation due to error propagation in decoding. We provide an in-depth analysis of these LLMs tailored for DocMT, examining translation errors, discourse phenomena, strategies for training and inference, the data efficiency of parallel documents, recent test set evaluations, and zero-shot crosslingual transfer. |
Minghao Wu; Thuy-Trang Vu; Lizhen Qu; George Foster; Gholamreza Haffari; | arxiv-cs.CL | 2024-01-12 |
| 292 | Machine Translation Models Are Zero-Shot Detectors of Translation Direction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we explore an unsupervised approach to translation direction detection based on the simple hypothesis that $p(\text{translation}|\text{original})>p(\text{original}|\text{translation})$, motivated by the well-known simplification effect in translationese or machine-translationese. |
Michelle Wastl; Jannis Vamvas; Rico Sennrich; | arxiv-cs.CL | 2024-01-12 |
| 293 | Lost in The Source Language: How Large Language Models Evaluate The Quality of Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task, aiming to better understand the mechanisms behind their remarkable performance in this task. |
XU HUANG et. al. | arxiv-cs.CL | 2024-01-12 |
| 294 | Towards Boosting Many-to-Many Multilingual Machine Translation with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we focus on boosting many-to-many multilingual translation of LLMs with an emphasis on zero-shot translation directions. |
Pengzhi Gao; Zhongjun He; Hua Wu; Haifeng Wang; | arxiv-cs.CL | 2024-01-11 |
| 295 | Addressing Data Scarcity Issue for English-Mizo Neural Machine Translation Using Data Augmentation and Language Model Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Low-resource language in machine translation systems poses multiple complications regarding accuracy in translation due to insufficient incorporation of linguistic information. … |
Vanlalmuansangi Khenglawt; Sahinur Rahman Laskar; Partha Pakray; Ajoy Kumar Khan; | J. Intell. Fuzzy Syst. | 2024-01-11 |
| 296 | Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This article introduces contrastive alignment instructions (AlignInstruct) to address two challenges in machine translation (MT) on large language models (LLMs). |
Zhuoyuan Mao; Yen Yu; | arxiv-cs.CL | 2024-01-11 |
| 297 | MirrorDiffusion: Stabilizing Diffusion Process in Zero-shot Image Translation By Prompts Redescription and Beyond Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To make reconstruction explicit, we propose a prompt redescription strategy to realize a mirror effect between the source and reconstructed image in the diffusion model (MirrorDiffusion). |
Yupei Lin; Xiaoyu Xian; Yukai Shi; Liang Lin; | arxiv-cs.CV | 2024-01-06 |
| 298 | Domain Dynamics: Evaluating Large Language Models in English-Hindi Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Large Language Models (LLMs) have demonstrated impressive capabilities in machine translation, leveraging extensive pre-training on vast amounts of data. However, this gener-alist … |
Soham Bhattacharjee; Baban Gain; Asif Ekbal; | Conference on Machine Translation | 2024-01-01 |
| 299 | Investigating The Linguistic Performance of Large Language Models in Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper summarizes the results of our test suite evaluation on 39 machine translation systems submitted at the Shared Task of the Ninth Conference of Machine Translation … |
SHUSHEN MANAKHIMOVA et. al. | Conference on Machine Translation | 2024-01-01 |
| 300 | Occiglot at WMT24: European Open-source Large Language Models Evaluated on Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This document describes the submission of the very first version of the Occiglot open-source large language model to the General MT Shared Task of the 9th Conference of Machine … |
ELEFTHERIOS AVRAMIDIS et. al. | Conference on Machine Translation | 2024-01-01 |
| 301 | NTTSU at WMT2024 General Translation Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The NTTSU team’s submission leverages several large language models developed through a training procedure that includes continual pre-training and supervised fine-tuning. For … |
MINATO KONDO et. al. | Conference on Machine Translation | 2024-01-01 |
| 302 | SCIR-MT’s Submission for WMT24 General Machine Translation Task Related Papers Related Patents Related Grants Related Venues Related Experts View |
Baohang Li; Zekai Ye; Yi-Chong Huang; Xiaocheng Feng; Bing Qin; | Conference on Machine Translation | 2024-01-01 |
| 303 | From General LLM to Translation: How We Dramatically Improve Translation Quality Using Human Evaluation Data for LLM Finetuning Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper describes Yandex submission to the WMT2024 General Translation Task. More specifically, we present a novel pipeline designed to build a strong paragraph-level … |
DENIS ELSHIN et. al. | Conference on Machine Translation | 2024-01-01 |
| 304 | CUNI at WMT24 General Translation Task: LLMs, (Q)LoRA, CPO and Model Merging Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper presents the contributions of Charles University teams to the WMT24 General Translation task (English to Czech, German and Russian, and Czech to Ukrainian) and the … |
MIROSLAV HRABAL et. al. | Conference on Machine Translation | 2024-01-01 |
| 305 | UvA-MT’s Participation in The WMT24 General Translation Shared Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Fine-tuning Large Language Models (FT-LLMs) with parallel data has emerged as a promising paradigm in recent machine translation research. In this paper, we explore the … |
Shaomu Tan; David Stap; Seth Aycock; C. Monz; Di Wu; | Conference on Machine Translation | 2024-01-01 |
| 306 | Document-level Translation with LLM Reranking: Team-J at WMT 2024 General Translation Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: We participated in the constrained track for English-Japanese and Japanese-Chinese translations at the WMT 2024 General Machine Translation Task. Our approach was to generate a … |
KEITO KUDO et. al. | Conference on Machine Translation | 2024-01-01 |
| 307 | TSU HITS’s Submissions to The WMT 2024 General Machine Translation Shared Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper describes the TSU HITS team’s submission system for the WMT’24 general translation task. We focused on exploring the capabilities of discrete diffusion models for the … |
Vladimir Mynka; Nikolay Mikhaylovskiy; | Conference on Machine Translation | 2024-01-01 |
| 308 | AlphaIntellect at SemEval-2024 Task 6: Detection of Hallucinations in Generated Text Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: One major issue in natural language generation (NLG) models is detecting hallucinations (semantically inaccurate outputs). This study investigates a hallucination detection system … |
Sohan Choudhury; Priyam Saha; Subharthi Ray; Shankha S. Das; Dipankar Das; | International Workshop on Semantic Evaluation | 2024-01-01 |
| 309 | How Far Can 100 Samples Go? Unlocking Zero-Shot Translation with Tiny Multi-Parallel Data Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Zero-shot translation aims to translate between language pairs not seen during training in Multilingual Machine Translation (MMT) and is widely considered an open problem. A … |
Di Wu; Shaomu Tan; Yan Meng; David Stap; C. Monz; | Annual Meeting of the Association for Computational … | 2024-01-01 |
| 310 | Hidetsune at SemEval-2024 Task 4: An Application of Machine Learning to Multilingual Propagandistic Memes Identification Using Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: In this system paper for SemEval-2024 Task4 subtask 2b, I present my approach to identifying propagandistic memes in multiple languages. I firstly establish a baseline for … |
Hidetsune Takahashi; | International Workshop on Semantic Evaluation | 2024-01-01 |
| 311 | Enabling Human-Centered Machine Translation Using Concept-Based Large Language Model Prompting and Translation Memory Related Papers Related Patents Related Grants Related Venues Related Experts View |
Ming Qian; Chuiqing Kong; | Interacción | 2024-01-01 |
| 312 | ASOS at NADI 2024 Shared Task: Bridging Dialectness Estimation and MSA Machine Translation for Arabic Language Enhancement Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This study undertakes a comprehensive investigation of transformer-based models to advance Arabic language processing, focusing on two pivotal aspects: the estimation of Arabic … |
Omer Nacar; Serry Sibaee; Abdullah Alharbi; L. Ghouti; Anis Koubaa; | ARABICNLP | 2024-01-01 |
| 313 | Enhancing Low-Resource NLP By Consistency Training With Data and Model Perturbations Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Natural language processing (NLP) has recently shown significant progress in rich-resource scenarios. However, it is much less effective for low-resource scenarios due to the … |
XIAOBO LIANG et. al. | IEEE/ACM Transactions on Audio, Speech, and Language … | 2024-01-01 |
| 314 | Naïve Bayes Approach for Word Sense Disambiguation System With A Focus on Parts-of-Speech Ambiguity Resolution Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Natural languages are written and spoken languages, and NLP (Natural Language Processing) is the ability of a computer program to recognize both written and spoken languages. Word … |
AJITH ABRAHAM et. al. | IEEE Access | 2024-01-01 |
| 315 | Improving LLM-based Machine Translation with Systematic Self-Correction IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). However, careful evaluations by human reveal that the translations produced by LLMs … |
ZHAOPENG FENG et. al. | ArXiv | 2024-01-01 |
| 316 | Findings of The WMT24 General Machine Translation Shared Task: The LLM Era Is Here But MT Is Not Solved Yet Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This overview paper presents the results of the General Machine Translation Task organised as part of the 2024 Conference on Machine Translation (WMT). In the general MT task, … |
TOM KOCMI et. al. | Conference on Machine Translation | 2024-01-01 |
| 317 | Findings of The WMT 2024 Biomedical Translation Shared Task: Test Sets on Abstract Level Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: We present the results of the ninth edition of the Biomedical Translation Task at WMT’24. We released test sets for six language pairs, namely, French, German, Italian, … |
MARIANA L. NEVES et. al. | Conference on Machine Translation | 2024-01-01 |
| 318 | IOL Research Machine Translation Systems for WMT24 General Machine Translation Shared Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper illustrates the submission system of the IOL Research team for the WMT24 General Machine Translation shared task. We submitted translations for all translation … |
Wenbo Zhang; | Conference on Machine Translation | 2024-01-01 |
| 319 | MSLC24 Submissions to The General Machine Translation Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The MSLC (Metric Score Landscape Challenge) submissions for English–German, English–Spanish, and Japanese–Chinese are constrained systems built using Transformer models for the … |
Samuel Larkin; Chi-liu Lo; Rebecca Knowles; | Conference on Machine Translation | 2024-01-01 |
| 320 | The Bangla/Bengali Seed Dataset Submission to The WMT24 Open Language Data Initiative Shared Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: We contribute a seed dataset for the Bangla/Bengali language as part of the WMT24 Open Language Data Initiative shared task. We validate the quality of the dataset against a mined … |
Firoz Ahmed; Nitin Venkateswaran; Sarah Moeller; | Conference on Machine Translation | 2024-01-01 |
| 321 | FLORES+ Translation and Machine Translation Evaluation for The Erzya Language Related Papers Related Patents Related Grants Related Venues Related Experts View |
Isai Gordeev; Sergey Kuldin; David Dale; | Conference on Machine Translation | 2024-01-01 |
| 322 | HW-TSC’s Participation in The WMT 2024 QEAPE Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The paper presents the submission by HW-TSC in the WMT 2024 Quality-informed Automatic Post Editing (QEAPE) shared task for the English-Hindi (En-Hi) and English-Tamil (En-Ta) … |
JIAWEI YU et. al. | Conference on Machine Translation | 2024-01-01 |
| 323 | A High-quality Seed Dataset for Italian Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper describes the submission of a high-quality translation of the OLDI Seed dataset into Italian for the WMT 2024 Open Language Data Initiative shared task. The base of … |
Edoardo Ferrante; | Conference on Machine Translation | 2024-01-01 |
| 324 | Enhancing Tuvan Language Resources Through The FLORES Dataset Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: FLORES is a benchmark dataset designed for evaluating machine translation systems, particularly for low-resource languages. This paper, conducted as a part of Open Language Data … |
Ali Kuzhuget; Airana Mongush; Nachyn-Enkhedorzhu Oorzhak; | Conference on Machine Translation | 2024-01-01 |
| 325 | Evaluating WMT 2024 Metrics Shared Task Submissions on AfriMTE (the African Challenge Set) Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The A FRI MTE challenge set from WMT 2024 Metrics Shared Task aims to evaluate the capabilities of evaluation metrics for machine translation on low-resource African languages, … |
Jiayi Wang; D. Adelani; Pontus Stenetorp; | Conference on Machine Translation | 2024-01-01 |
| 326 | SRIB-NMT’s Submission to The Indic MT Shared Task in WMT 2024 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: In the context of the Indic Low Resource Machine Translation (MT) challenge at WMT-24 ((Pakray et al., 2024)), we participated in four language pairs: English-Assamese (en-as), … |
Pranamya Patil; Raghavendra Hr; Aditya Raghuwanshi; Kushal Verma; | Conference on Machine Translation | 2024-01-01 |
| 327 | DLUT-NLP Machine Translation Systems for WMT24 Low-Resource Indic Language Translation Related Papers Related Patents Related Grants Related Venues Related Experts View |
Chenfei Ju; Junpeng Liu; Kaiyu Huang; Degen Huang; | Conference on Machine Translation | 2024-01-01 |
| 328 | MTNLP-IIITH: Machine Translation for Low-Resource Indic Languages Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Machine Translation for low-resource languages poses significant challenges, primarily due to the limited availability of data.The WMT24 Low-Resource Indic Neural Machine … |
Abhinav P M; Ketaki Shetye; Parameswari Krishnamurthy; | Conference on Machine Translation | 2024-01-01 |
| 329 | MSLC24: Further Challenges for Metrics on A Wide Landscape of Translation Quality Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: In this second edition of the Metric Score Land-scape Challenge (MSLC), we examine how automatic metrics for machine translation perform on a wide variety of machine translation … |
Rebecca Knowles; Samuel Larkin; Chi-kiu Lo; | Conference on Machine Translation | 2024-01-01 |
| 330 | Findings of The WMT 2024 Shared Task on Non-Repetitive Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The repetition of words in an English sentence can create a monotonous or awkward impression. In such cases, repetition should be avoided appropriately. To evaluate the … |
Kazutaka Kinugawa; Hideya Mino; Isao Goto; Naoto Shirai; | Conference on Machine Translation | 2024-01-01 |
| 331 | Findings of WMT 2024’s MultiIndic22MT Shared Task for Machine Translation of 22 Indian Languages Related Papers Related Patents Related Grants Related Venues Related Experts View |
Raj Dabre; Anoop Kunchukuttan; | Conference on Machine Translation | 2024-01-01 |
| 332 | Findings of WMT 2024 Shared Task on Low-Resource Indic Languages Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper presents the results of the low-resource Indic language translation task, organized in conjunction with the Ninth Conference on Machine Translation (WMT) 2024. In this … |
PARTHA PAKRAY et. al. | Conference on Machine Translation | 2024-01-01 |
| 333 | Spanish Corpus and Provenance with Computer-Aided Translation for The WMT24 OLDI Shared Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper presents the S EED -CAT submission to the WMT24 Open Language Data Initiative shared task. We detail our data collection method, which involves a computer-aided … |
Jose Cols; | Conference on Machine Translation | 2024-01-01 |
| 334 | English-to-Low-Resource Translation: A Multimodal Approach for Hindi, Malayalam, Bengali, and Hausa Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Multimodal machine translation leverages multiple data modalities to enhance translation quality, particularly for low-resourced languages. This paper uses a multimodal model that … |
ALI HATAMI et. al. | Conference on Machine Translation | 2024-01-01 |
| 335 | Tulu Language Text Recognition and Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Language is a primary means of communication, but it is not the only means; knowing a language does, however, assist speed up the process. Many distinct languages are spoken … |
.. Prathwini; Anisha P. Rodrigues; P. Vijaya; Roshan Fernandes; | IEEE Access | 2024-01-01 |
| 336 | An Intelligent Error Detection Model for Machine Translation Using Composite Neural Network-Based Semantic Perception Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Although machine translation has received great progress in recent years, machine translation results usually existed some errors due to the complex relationship between sentence … |
Yaoxi Wu; Qiao Liang; | IEEE Access | 2024-01-01 |
| 337 | SYSTRAN @ WMT24 Non-Repetitive Translation Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Many contemporary NLP systems rely on neural decoders for text generation, which demonstrate an impressive ability to generate text approaching human fluency levels. However, in … |
Marko Avila; Josep Crego; | Conference on Machine Translation | 2024-01-01 |
| 338 | Mediapi-RGB: Enabling Technological Breakthroughs in French Sign Language (LSF) Research Through An Extensive Video-Text Corpus Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Abstract: We introduce Mediapi-RGB, a new dataset of French Sign Language (LSF) along with the first LSF-to-French machine translation model. With 86 hours of video, it the largest LSF … |
YANIS OUAKRIM et. al. | VISIGRAPP : VISAPP | 2024-01-01 |
| 339 | Research on Automatic Identification of Machine English Translation Errors Based on Improved GLR Algorithm Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Machine translation is a powerful tool for overcoming linguistic obstacles, but it often introduces errors that lower the overall translation quality. This research project aims … |
Guanghuan Li; | Informatica (Slovenia) | 2024-01-01 |
| 340 | NovelTrans: System for WMT24 Discourse-Level Literary Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper describes our submission system, NovelTrans, from NLP 2 CT and DeepTranx for the WMT24 Discourse-Level Literary Translation Task in Chinese-English, Chinese-German, and … |
Yuchen Liu; Yutong Yao; Runzhe Zhan; Yuchu Lin; Derek F. Wong; | Conference on Machine Translation | 2024-01-01 |
| 341 | Context-Aware Linguistic Steganography Model Based on Neural Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Linguistic steganography based on text generation is a hot topic in the field of text information hiding. Previous studies have managed to improve the syntactic quality of … |
CHANGHAO DING et. al. | IEEE/ACM Transactions on Audio, Speech, and Language … | 2024-01-01 |
| 342 | HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we release an annotated dataset for the hallucination and omission phenomena covering 18 translation directions with varying resource levels and scripts. |
DAVID DALE et. al. | emnlp | 2023-12-22 |
| 343 | Program Translation Via Code Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a novel model called Code Distillation (CoDist) whereby we capture the semantic and structural equivalence of code in a language agnostic intermediate representation. |
YUFAN HUANG et. al. | emnlp | 2023-12-22 |
| 344 | MMNMT: Modularizing Multilingual Neural Machine Translation with Flexibly Assembled MoE and Dense Blocks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a modularized MNMT framework that is able to flexibly assemble dense and MoE-based sparse modules to achieve the best of both worlds. |
SHANGJIE LI et. al. | emnlp | 2023-12-22 |
| 345 | Towards A Better Understanding of Variations in Zero-Shot Neural Machine Translation Performance Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Through systematic experimentation, spanning 1,560 language directions across 40 languages, we identify three key factors contributing to high variations in ZS NMT performance: 1) target-side translation quality, 2) vocabulary overlap, and 3) linguistic properties. |
Shaomu Tan; Christof Monz; | emnlp | 2023-12-22 |
| 346 | MT2: Towards A Multi-Task Machine Translation Model with Translation-Specific In-Context Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Most of the previous work uses separate models or methods to solve these tasks, which is not conducive to knowledge transfer of different tasks and increases the complexity of system construction. In this work, we explore the potential of pre-trained language model in machine translation tasks and propose a Multi-Task Machine Translation (MT2) model to integrate these translation tasks. |
CHUNYOU LI et. al. | emnlp | 2023-12-22 |
| 347 | Revisiting Machine Translation for Cross-lingual Classification IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show that, by using a stronger MT system and mitigating the mismatch between training on original text and running inference on machine translated text, translate-test can do substantially better than previously assumed. |
Mikel Artetxe; Vedanuj Goswami; Shruti Bhosale; Angela Fan; Luke Zettlemoyer; | emnlp | 2023-12-22 |
| 348 | A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices. In this work, we address this gap by investigating whether and to what extent such models exhibit gender bias in machine translation and how we can mitigate it. |
Giuseppe Attanasio; Flor Plaza del Arco; Debora Nozza; Anne Lauscher; | emnlp | 2023-12-22 |
| 349 | Hi Guys or Hi Folks? Benchmarking Gender-Neutral Machine Translation with The GeNTE Corpus IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Based on GeNTE, we then overview existing reference-based evaluation approaches, highlight their limits, and propose a reference-free method more suitable to assess gender-neutral translation. |
Andrea Piergentili; Beatrice Savoldi; Dennis Fucci; Matteo Negri; Luisa Bentivogli; | emnlp | 2023-12-22 |
| 350 | Learn and Consolidate: Continual Adaptation for Zero-Shot and Multilingual Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a two-stage approach that encourages original models to acquire language-agnostic multilingual representations from new data, and preserves the model architecture without introducing parameters. |
Kaiyu Huang; Peng Li; Junpeng Liu; Maosong Sun; Yang Liu; | emnlp | 2023-12-22 |
| 351 | Crossing The Threshold: Idiomatic Machine Translation Through Retrieval Augmentation and Loss Weighting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To improve translation of natural idioms, we introduce two straightforward yet effective techniques: the strategic upweighting of training loss on potentially idiomatic sentences, and using retrieval-augmented models. |
Emmy Liu; Aditi Chaudhary; Graham Neubig; | emnlp | 2023-12-22 |
| 352 | On The Use of Metaphor Translation in Psychiatry Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Now, metaphor has been shown to be paramount in both identifying individuals struggling with mental problems and helping those individuals understand and communicate their experiences. Therefore, this paper aims to survey the potential of Machine Translation for providing equitable psychiatric healthcare and highlights the need for further research on the transferability of existing machine and metaphor translation research in the domain of psychiatry. |
Lois Wong; | arxiv-cs.CL | 2023-12-22 |
| 353 | Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, when it comes to non-English languages, the quantity and quality of textual information are comparatively scarce. To address this issue, we introduce the novel task of automatic Knowledge Graph Completion (KGE) and perform a thorough investigation on bridging the gap in both the quantity and quality of textual information between English and non-English languages. |
SIMONE CONIA et. al. | emnlp | 2023-12-22 |
| 354 | DecoMT: Decomposed Prompting for Machine Translation Between Related Languages Using Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce DecoMT, a novel approach of few-shot prompting that decomposes the translation process into a sequence of word chunk translations. |
Ratish Puduppully; Anoop Kunchukuttan; Raj Dabre; Ai Ti Aw; Nancy Chen; | emnlp | 2023-12-22 |
| 355 | PromptST: Abstract Prompt Learning for End-to-End Speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we take the first step toward understanding the fusion of speech and text features in S2T model. |
TENGFEI YU et. al. | emnlp | 2023-12-22 |
| 356 | Challenges in Context-Aware Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we investigate and present several core challenges that impede progress within the field, relating to discourse phenomena, context usage, model architectures, and document-level evaluation. |
Linghao Jin; Jacqueline He; Jonathan May; Xuezhe Ma; | emnlp | 2023-12-22 |
| 357 | Video-Helpful Multimodal Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce EVA (Extensive training set and Video-helpful evaluation set for Ambiguous subtitles translation), an MMT dataset containing 852k Japanese-English parallel subtitle pairs, 520k Chinese-English parallel subtitle pairs, and corresponding video clips collected from movies and TV episodes. |
Yihang Li; Shuichiro Shimizu; Chenhui Chu; Sadao Kurohashi; Wei Li; | emnlp | 2023-12-22 |
| 358 | CLAD-ST: Contrastive Learning with Adversarial Data for Robust Speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We address this robustness problem in downstream MT models by forcing the MT encoder to bring the representations of a noisy input closer to its clean version in the semantic space. This is achieved by introducing a contrastive learning method that leverages adversarial examples in the form of ASR outputs paired with their corresponding human transcripts to optimize the network parameters. |
Sathish Indurthi; Shamil Chollampatt; Ravi Agrawal; Marco Turchi; | emnlp | 2023-12-22 |
| 359 | An Empirical Study of Translation Hypothesis Ensembling with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we investigate how hypothesis ensembling can improve the quality of the generated text for the specific problem of LLM-based machine translation. |
Ant�nio Farinhas; Jos� de Souza; Andre Martins; | emnlp | 2023-12-22 |
| 360 | Multilingual K-Nearest-Neighbor Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, these improvements have been limited to high-resource language pairs, with large datastores, and remain a challenge for low-resource languages. In this paper, we address this issue by combining representations from multiple languages into a single datastore. |
David Stap; Christof Monz; | emnlp | 2023-12-22 |
| 361 | Document-Level Machine Translation with Large Language Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: The study focuses on three aspects: 1) Effects of Context-Aware Prompts, where we investigate the impact of different prompts on document-level translation quality and discourse phenomena; 2) Comparison of Translation Models, where we compare the translation performance of ChatGPT with commercial MT systems and advanced document-level MT methods; 3) Analysis of Discourse Modelling Abilities, where we further probe discourse knowledge encoded in LLMs and shed light on impacts of training techniques on discourse modeling. |
LONGYUE WANG et. al. | emnlp | 2023-12-22 |
| 362 | PROSE: A Pronoun Omission Solution for Chinese-English Spoken Language Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To alleviate the negative impact introduced by pro-drop, we propose Mention-Aware Semantic Augmentation, a novel approach that leverages the semantic embedding of dropped pronouns to augment training pairs. |
Ke Wang; Xiutian Zhao; Yanghui Li; Wei Peng; | emnlp | 2023-12-22 |
| 363 | Exploring Discourse Structure in Document-level Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a more sound paragraph-to-paragraph translation mode and explore whether discourse structure can improve DocMT. |
Xinyu Hu; Xiaojun Wan; | emnlp | 2023-12-22 |
| 364 | Contextual Code Switching for Machine Translation Using Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present an extensive study on the code switching task specifically for the machine translation task comparing multiple LLMs. |
Arshad Kaji; Manan Shah; | arxiv-cs.CL | 2023-12-20 |
| 365 | An Empirical Study of Unsupervised Neural Machine Translation: Analyzing NMT Output, Model’s Behavior and Sentences’ Contribution Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We focus on three very diverse languages, French, Gujarati, and Kazakh, and train bilingual NMT models, to and from English, with various levels of supervision, in high- and low- resource setups, measure quality of the NMT output and compare the generated sequences’ word order and semantic similarity to source and reference sentences. |
Isidora Chara Tourni; Derry Wijaya; | arxiv-cs.CL | 2023-12-19 |
| 366 | Fine-tuning Large Language Models for Adaptive Machine Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents the outcomes of fine-tuning Mistral 7B, a general-purpose large language model (LLM), for adaptive machine translation (MT). |
Yasmin Moslem; Rejwanul Haque; Andy Way; | arxiv-cs.CL | 2023-12-19 |
| 367 | Predicting Human Translation Difficulty with Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We find that surprisal and attention are complementary predictors of translation difficulty, and that surprisal derived from a NMT model is the single most successful predictor of production duration. |
Zheng Wei Lim; Ekaterina Vylomova; Charles Kemp; Trevor Cohn; | arxiv-cs.CL | 2023-12-18 |
| 368 | Overview of MTIL Track at FIRE 2023: Machine Translation for Indian Languages Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The objective of the MTIL track in FIRE 2023 was to encourage the development of Indian Language to Indian Language (IL-IL) Neural Machine Translation models. The languages … |
SURUPENDU GANGOPADHYAY et. al. | Proceedings of the 15th Annual Meeting of the Forum for … | 2023-12-15 |
| 369 | Neural Machine Translation of Clinical Text: An Empirical Investigation Into Multilingual Pre-Trained Language Models and Transfer-Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We conduct investigations on clinical text machine translation by examining multilingual neural network models using deep learning such as Transformer based structures. |
LIFENG HAN et. al. | arxiv-cs.CL | 2023-12-12 |
| 370 | Performance Evaluation of Popular Deep Neural Networks for Neural Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The field of Neural Machine Translation (NMT) has shown impressive performance for quick and easy communication in various languages spoken all over the world. NMT helps us by … |
MUHAMMAD NAEEM et. al. | 2023 International Conference on Frontiers of Information … | 2023-12-11 |
| 371 | Design of Automatic Translation System for English for Special Purpose in Agriculture Based on Neural Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Agricultural terms have some unique characteristics, which make them need special treatment in machine translation. Agriculture is a highly specialized field, with a large number … |
Meilin Wang; | Proceedings of the 3rd International Conference on … | 2023-12-08 |
| 372 | Converting Epics/Stories Into Pseudocode Using Transformers Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: With this research paper, we aim to present a methodology to generate pseudocode from a given agile user story of small functionalities so as to reduce the overall time spent on the industrial project. |
Gaurav Kolhatkar; Akshit Madan; Nidhi Kowtal; Satyajit Roy; Sheetal Sonawane; | arxiv-cs.CL | 2023-12-08 |
| 373 | Improving Neural Machine Translation By Multi-Knowledge Integration with Prompting Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we focus on how to integrate multi-knowledge, multiple types of knowledge, into NMT models to enhance the performance with prompting. |
Ke Wang; Jun Xie; Yuqi Zhang; Yu Zhao; | arxiv-cs.CL | 2023-12-07 |
| 374 | First Attempt at Building Parallel Corpora for Machine Translation of Northeast India’s Very Low-Resource Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents the creation of initial bilingual corpora for thirteen very low-resource languages of India, all from Northeast India. |
Atnafu Lambebo Tonja; Melkamu Mersha; Ananya Kalita; Olga Kolesnikova; Jugal Kalita; | arxiv-cs.CL | 2023-12-07 |
| 375 | Making Translators Privacy-aware on The User’s Side Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose PRISM to enable users of machine translation systems to preserve the privacy of data on their own initiative. |
Ryoma Sato; | arxiv-cs.CR | 2023-12-07 |
| 376 | Efficient Monotonic Multihead Attention Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce the Efficient Monotonic Multihead Attention (EMMA), a state-of-the-art simultaneous translation model with numerically-stable and unbiased monotonic alignment estimation. |
Xutai Ma; Anna Sun; Siqi Ouyang; Hirofumi Inaguma; Paden Tomasello; | arxiv-cs.CL | 2023-12-07 |
| 377 | Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address key challenges facing LLMs fine-tuned for SimulMT, validate classical SimulMT concepts and practices in the context of LLMs, explore adapting LLMs that are fine-tuned for NMT to the task of SimulMT, and introduce Simul-LLM, the first open-source fine-tuning and evaluation pipeline development framework for LLMs focused on SimulMT. |
Victor Agostinelli; Max Wild; Matthew Raffel; Kazi Ahmed Asif Fuad; Lizhong Chen; | arxiv-cs.CL | 2023-12-07 |
| 378 | English-Arabic Text Translation and Abstractive Summarization Using Transformers Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The vast growth of online and offline data has revolutionized how we gather, evaluate, and understand information. Comprehending lengthy text documents and extracting crucial … |
Heidi Ahmed Holiel; Nancy Mohamed; Arwa Ahmed; Walaa Medhat; | 2023 20th ACS/IEEE International Conference on Computer … | 2023-12-04 |
| 379 | End-to-End Speech-to-Text Translation: A Survey Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: As a result, researchers have been exploring end-to-end (E2E) models for ST translation. |
Nivedita Sethiya; Chandresh Kumar Maurya; | arxiv-cs.CL | 2023-12-02 |
| 380 | Beyond Lexical Consistency: Preserving Semantic Consistency for Program Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Program translation aims to convert the input programs from one programming language to another. Automatic program translation is a prized target of software engineering research, … |
Yali Du; Yiwei Ma; Zheng Xie; Ming Li; | 2023 IEEE International Conference on Data Mining (ICDM) | 2023-12-01 |
| 381 | Quick Back-Translation for Unsupervised Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose a two-for-one improvement to Transformer back-translation: Quick Back-Translation (QBT). |
Benjamin Brimacombe; Jiawei Zhou; | arxiv-cs.CL | 2023-12-01 |
| 382 | Relevance-guided Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an explainability-based training approach for NMT, applied in Unsupervised and Supervised model training, for translation of three languages of varying resources, French, Gujarati, Kazakh, to and from English. |
Isidora Chara Tourni; Derry Wijaya; | arxiv-cs.CL | 2023-11-30 |
| 383 | Women Are Beautiful, Men Are Leaders: Gender Stereotypes in Machine Translation and Language Modeling Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present GEST — a new manually created dataset designed to measure gender-stereotypical reasoning in language models and machine translation systems. |
Matúš Pikuliak; Andrea Hrckova; Stefan Oresko; Marián Šimko; | arxiv-cs.CL | 2023-11-30 |
| 384 | INarIG: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose the INarIG (Iterative Non-autoregressive Instruct Generation) model, which constructs the human typed sequence into Instruction Unit and employs iterative decoding with subwords to fully utilize input information given in the task. |
HENGCHAO SHANG et. al. | arxiv-cs.CL | 2023-11-29 |
| 385 | AdaptMLLM: Fine-Tuning Multilingual Language Models on Low-Resource Languages with Integrated LLM Playgrounds IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Abstract: The advent of Multilingual Language Models (MLLMs) and Large Language Models (LLMs) has spawned innovation in many areas of natural language processing. Despite the exciting … |
Séamus Lankford; Haithem Afli; Andy Way; | Inf. | 2023-11-29 |
| 386 | A Benchmark for Evaluating Machine Translation Metrics on Dialects Without Standard Orthography Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we evaluate how robust metrics are to non-standardized dialects, i.e. spelling differences in language varieties that do not have a standard orthography. |
Noëmi Aepli; Chantal Amrhein; Florian Schottmann; Rico Sennrich; | arxiv-cs.CL | 2023-11-28 |
| 387 | Reducing Gender Bias in Machine Translation Through Counterfactual Data Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We also propose a novel domain-adaptation technique that leverages in-domain data created with the counterfactual data generation techniques proposed by Zmigrod et al. (2019) to further improve accuracy on the WinoMT challenge test set without significant loss in translation quality. We show its effectiveness in NMT systems from English into three morphologically rich languages French, Spanish, and Italian. |
Ranjita Naik; Spencer Rarrick; Vishal Chowdhary; | arxiv-cs.CL | 2023-11-27 |
| 388 | Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, when it comes to non-English languages, the quantity and quality of textual information are comparatively scarce. To address this issue, we introduce the novel task of automatic Knowledge Graph Enhancement (KGE) and perform a thorough investigation on bridging the gap in both the quantity and quality of textual information between English and non-English languages. |
SIMONE CONIA et. al. | arxiv-cs.AI | 2023-11-27 |
| 389 | Improving Word Sense Disambiguation in Neural Machine Translation with Salient Document Context Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a simple and scalable approach to resolve translation ambiguity by incorporating a small amount of extra-sentential context in neural \mt. Our approach requires no sense annotation and no change to standard model architectures. |
Elijah Rippeth; Marine Carpuat; Kevin Duh; Matt Post; | arxiv-cs.CL | 2023-11-26 |
| 390 | Machine Translation to Control Formality Features in The Target Language Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: When a language translation technique is used to translate from a source language that does not pertain the formality (e.g. English) to a target language that does, there is a missing information on formality that could be a challenge in producing an accurate outcome. This research explores how this issue should be resolved when machine learning methods are used to translate from English to languages with formality, using Hindi as the example data. |
Harshita Tyagi; Prashasta Jung; Hyowon Lee; | arxiv-cs.CL | 2023-11-22 |
| 391 | Context-aware Neural Machine Translation for English-Japanese Business Scene Dialogues Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we explore how context-awareness can improve the performance of the current Neural Machine Translation (NMT) models for English-Japanese business dialogues translation, and what kind of context provides meaningful information to improve translation. |
Sumire Honda; Patrick Fernandes; Chrysoula Zerva; | arxiv-cs.CL | 2023-11-20 |
| 392 | Multi-Task Self-Supervised Learning Based Tibetan-Chinese Speech-to-Speech Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Speech-to-speech translation tasks are commonly tackled by using a three-level cascade system which comprises of speech recognition, machine translation, and speech synthesis. … |
Rouhe Liu; Yue Zhao; Xiaona Xu; | 2023 International Conference on Asian Language Processing … | 2023-11-18 |
| 393 | Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Despite extensive study into translating Bangla to English, English to Bangla, and Banglish to Bangla in the past, there has been a noticeable gap in translating Bangla regional dialects into standard Bangla. In this study, we set out to fill this gap by creating a collection of 32,500 sentences, encompassing Bangla, Banglish, and English, representing five regional Bangla dialects. |
FATEMA TUJ JOHORA FARIA et. al. | arxiv-cs.CL | 2023-11-18 |
| 394 | SentAlign: Accurate and Scalable Sentence Alignment Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present SentAlign, an accurate sentence alignment tool designed to handle very large parallel document pairs. |
Steinþór Steingrímsson; Hrafn Loftsson; Andy Way; | arxiv-cs.CL | 2023-11-15 |
| 395 | English–Vietnamese Machine Translation Using Deep Learning for Chatbot Applications Related Papers Related Patents Related Grants Related Venues Related Experts View |
Sakya Tuan; P. Meesad; Ha Huy Cuong Nguyen; | SN Computer Science | 2023-11-15 |
| 396 | Assessing Translation Capabilities of Large Language Models Involving English and Indian Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, our aim is to explore the multilingual capabilities of large language models by using machine translation as a task involving English and 22 Indian languages. |
VANDAN MUJADIA et. al. | arxiv-cs.CL | 2023-11-15 |
| 397 | Evaluating Gender Bias in The Translation of Gender-Neutral Languages Into English Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite numerous studies into gender bias in translations from gender-neutral languages such as Turkish into more strongly gendered languages like English, there are no benchmarks for evaluating this phenomenon or for assessing mitigation strategies. To address this gap, we introduce GATE X-E, an extension to the GATE (Rarrick et al., 2023) corpus, that consists of human translations from Turkish, Hungarian, Finnish, and Persian into English. |
Spencer Rarrick; Ranjita Naik; Sundar Poudel; Vishal Chowdhary; | arxiv-cs.CL | 2023-11-15 |
| 398 | Extending Multilingual Machine Translation Through Imitation Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We aim to extend large-scale MNMT models to a new language, allowing for translation between the newly added and all of the already supported languages in a challenging scenario: using only a parallel corpus between the new language and English. |
Wen Lai; Viktor Hangya; Alexander Fraser; | arxiv-cs.CL | 2023-11-14 |
| 399 | On-the-Fly Fusion of Large Language Models and Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose the on-the-fly ensembling of a machine translation model with an LLM, prompted on the same task and input. |
Hieu Hoang; Huda Khayrallah; Marcin Junczys-Dowmunt; | arxiv-cs.CL | 2023-11-14 |
| 400 | Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Pivoting via high-resource languages remains a strong strategy for low-resource directions, and in this paper we revisit ways of pivoting through multiple languages. |
Alireza Mohammadshahi; Jannis Vamvas; Rico Sennrich; | arxiv-cs.CL | 2023-11-13 |
| 401 | Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Added toxicity in the context of translation refers to the fact of producing a translation output with more toxicity than there exists in the input. In this paper, we present MinTox which is a novel pipeline to identify added toxicity and mitigate this issue which works at inference time. |
Marta R. Costa-jussà; David Dale; Maha Elbayad; Bokai Yu; | arxiv-cs.CL | 2023-11-11 |
| 402 | Gender Inflected or Bias Inflicted: On Using Grammatical Gender Cues for Bias Evaluation in Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To demonstrate our point, in this work, we use Hindi as the source language and construct two sets of gender-specific sentences: OTSC-Hindi and WinoMT-Hindi that we use to evaluate different Hindi-English (HI-EN) NMT systems automatically for gender bias. |
Pushpdeep Singh; | arxiv-cs.CL | 2023-11-07 |
| 403 | Findings of The WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in The Cosmos of LLMs IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We employ both automatic and human evaluations to measure the performance of the submitted systems. |
LONGYUE WANG et. al. | arxiv-cs.CL | 2023-11-06 |
| 404 | CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Training Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a Confidence-Based Simultaneous Machine Translation (CBSiMT) framework, which uses model confidence to perceive hallucination tokens and mitigates their negative impact with weighted prefix-to-prefix training. |
MENGGE LIU et. al. | arxiv-cs.CL | 2023-11-06 |
| 405 | Bilingual Corpus Mining and Multistage Fine-Tuning for Improving Machine Translation of Lecture Transcripts Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To create the parallel corpora, we propose a dynamic programming based sentence alignment algorithm which leverages the cosine similarity of machine-translated sentences. |
Haiyue Song; Raj Dabre; Chenhui Chu; Atsushi Fujita; Sadao Kurohashi; | arxiv-cs.CL | 2023-11-06 |
| 406 | Replicable Benchmarking of Neural Machine Translation (NMT) on Low-Resource Local Languages in Indonesia Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Neural machine translation (NMT) for low-resource local languages in Indonesia faces significant challenges, including the need for a representative benchmark and limited data availability. This work addresses these challenges by comprehensively analyzing training NMT systems for four low-resource local languages in Indonesia: Javanese, Sundanese, Minangkabau, and Balinese. |
Lucky Susanto; Ryandito Diandaru; Adila Krisnadhi; Ayu Purwarianti; Derry Wijaya; | arxiv-cs.CL | 2023-11-02 |
| 407 | Is Robustness Transferable Across Languages in Multilingual Neural Machine Translation? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we investigate the transferability of robustness across different languages in multilingual neural machine translation. |
Leiyu Pan; Deyi Xiong; | arxiv-cs.AI | 2023-10-31 |
| 408 | Towards A Deep Understanding of Multilingual End-to-End Speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we employ Singular Value Canonical Correlation Analysis (SVCCA) to analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages. |
Haoran Sun; Xiaohu Zhao; Yikun Lei; Shaolin Zhu; Deyi Xiong; | arxiv-cs.CL | 2023-10-31 |
| 409 | Gex’ez-English Bi-Directional Neural Machine Translation Using Transformer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Machine translation is the technique of translating texts from one language to another without human intervention using artificial intelligence. Neural Machine Translation (NMT) … |
Sefineh Getachew; Yirga Yayeh; | 2023 International Conference on Information and … | 2023-10-26 |
| 410 | Cultural Adaptation of Recipes Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a new task involving the translation and cultural adaptation of recipes between Chinese and English-speaking cuisines. |
YONG CAO et. al. | arxiv-cs.CL | 2023-10-26 |
| 411 | DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European Languages Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Towards the goal of multilingual disfluency correction, we present a high-quality human-annotated DC corpus covering four important Indo-European languages: English, Hindi, German and French. |
Vineet Bhat; Preethi Jyothi; Pushpak Bhattacharyya; | arxiv-cs.CL | 2023-10-25 |
| 412 | CUNI Submission to MRL 2023 Shared Task on Multi-lingual Multi-task Information Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To keep the inferred tags on the correct positions in the original language, we propose a method based on scoring the candidate positions using a label-sensitive translation model. |
Jindřich Helcl; Jindřich Libovický; | arxiv-cs.CL | 2023-10-25 |
| 413 | ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present ComSL, a speech-language model built atop a composite architecture of public pre-trained speech-only and language-only models and optimized data-efficiently for spoken language tasks. |
CHENYANG LE et. al. | nips | 2023-10-24 |
| 414 | Machine Translation for Nko: Tools, Corpora and Baseline Results Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Currently, there is no usable machine translation system for Nko, a language spoken by tens of millions of people across multiple West African countries, which holds significant cultural and educational value. To address this issue, we present a set of tools, resources, and baseline results aimed towards the development of usable machine translation systems for Nko and other languages that do not currently have sufficiently large parallel text corpora available. |
MOUSSA KOULAKO BALA DOUMBOUYA et. al. | arxiv-cs.CL | 2023-10-24 |
| 415 | Non-autoregressive Machine Translation with Probabilistic Context-free Grammar Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, conventional NAT models suffer from limited-expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens. |
SHANGTONG GUI et. al. | nips | 2023-10-24 |
| 416 | Data Augmentation Techniques for Machine Translation of Code-Switched Texts: A Comparative Study Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we compare three popular approaches: lexical replacements, linguistic theories, and back-translation (BT), in the context of Egyptian Arabic-English CSW. |
Injy Hamed; Nizar Habash; Ngoc Thang Vu; | arxiv-cs.CL | 2023-10-23 |
| 417 | Domain Terminology Integration Into Machine Translation: Leveraging Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper discusses the methods that we used for our submissions to the WMT 2023 Terminology Shared Task for German-to-English (DE-EN), English-to-Czech (EN-CS), and Chinese-to-English (ZH-EN) language pairs. |
D. Kelleher; | arxiv-cs.CL | 2023-10-22 |
| 418 | Boosting Unsupervised Machine Translation with Pseudo-Parallel Data Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a training strategy that relies on pseudo-parallel sentence pairs mined from monolingual corpora in addition to synthetic sentence pairs back-translated from monolingual corpora. |
Ivana Kvapilíková; Ondřej Bojar; | arxiv-cs.CL | 2023-10-22 |
| 419 | Evaluating and Optimizing The Effectiveness of Neural Machine Translation in Supporting Code Retrieval Models: A Study on The CAT Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we analyze the performance of NMT in natural language-to-code translation in the newly curated CAT benchmark[31] that includes the optimized versions of three Java datasets TLCodeSum, CodeSearchNet, Funcom, and a Python dataset PCSD. |
Hung Phan; Ali Jannesari; | cikm | 2023-10-21 |
| 420 | Code-Switching with Word Senses for Pretraining in Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce Word Sense Pretraining for Neural Machine Translation (WSP-NMT) – an end-to-end approach for pretraining multilingual NMT models leveraging word sense-specific information from Knowledge Bases. |
Vivek Iyer; Edoardo Barba; Alexandra Birch; Jeff Z. Pan; Roberto Navigli; | arxiv-cs.CL | 2023-10-21 |
| 421 | Translation Performance from The User’s Perspective of Large Language Models and Neural Machine Translation Systems Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The rapid global expansion of ChatGPT, which plays a crucial role in interactive knowledge sharing and translation, underscores the importance of comparative performance … |
Jungha Son; Boyoung Kim; | Inf. | 2023-10-19 |
| 422 | A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices. In this work, we address this gap by investigating whether and to what extent such models exhibit gender bias in machine translation and how we can mitigate it. |
Giuseppe Attanasio; Flor Miriam Plaza-del-Arco; Debora Nozza; Anne Lauscher; | arxiv-cs.CL | 2023-10-18 |
| 423 | Knn-seq: Efficient, Extensible KNN-MT Framework Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present an efficient and extensible kNN-MT framework, knn-seq, for researchers and developers that is carefully designed to run efficiently, even with a billion-scale large datastore. |
HIROYUKI DEGUCHI et. al. | arxiv-cs.CL | 2023-10-18 |
| 424 | Direct Neural Machine Translation with Task-level Mixture of Experts Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we examine Task-level MoE’s applicability in direct NMT and propose a series of high-performing training and evaluation configurations, through which Task-level MoE-based direct NMT systems outperform bilingual and pivot-based models for a large number of low and high-resource direct pairs, and translation directions. |
Isidora Chara Tourni; Subhajit Naskar; | arxiv-cs.CL | 2023-10-18 |
| 425 | An Empirical Study of Translation Hypothesis Ensembling with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we investigate how hypothesis ensembling can improve the quality of the generated text for the specific problem of LLM-based machine translation. |
António Farinhas; José G. C. de Souza; André F. T. Martins; | arxiv-cs.CL | 2023-10-17 |
| 426 | Long-form Simultaneous Speech Translation: Thesis Proposal Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This thesis proposal addresses end-to-end simultaneous speech translation, particularly in the long-form setting, i.e., without pre-segmentation. We present a survey of the latest advancements in E2E SST, assess the primary obstacles in SST and its relevance to long-form scenarios, and suggest approaches to tackle these challenges. |
Peter Polák; | arxiv-cs.CL | 2023-10-17 |
| 427 | Exploring Automatic Evaluation Methods Based on A Decoder-based LLM for Text Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper compares various methods, including tuning with encoder-based models and large language models under equal conditions, on two different tasks, machine translation evaluation and semantic textual similarity, in two languages, Japanese and English. |
Tomohito Kasahara; Daisuke Kawahara; | arxiv-cs.CL | 2023-10-17 |
| 428 | UvA-MT’s Participation in The WMT23 General Translation Shared Task Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes the UvA-MT’s submission to the WMT 2023 shared task on general machine translation. |
Di Wu; Shaomu Tan; David Stap; Ali Araabi; Christof Monz; | arxiv-cs.CL | 2023-10-15 |
| 429 | UvA-MT’s Participation in The WMT 2023 General Translation Shared Task Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper describes the UvA-MT’s submission to the WMT 2023 shared task on general machine translation. We participate in the constrained track in two directions: English … |
Di Wu; Shaomu Tan; David Stap; Ali Araabi; C. Monz; | ArXiv | 2023-10-15 |
| 430 | MILPaC: A Novel Benchmark for Evaluating Translation of Legal Text to Indian Languages Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we construct the first high-quality legal parallel corpus containing aligned text units in English and nine Indian languages, that includes several low-resource languages. |
Sayan Mahapatra; Debtanu Datta; Shubham Soni; Adrijit Goswami; Saptarshi Ghosh; | arxiv-cs.CL | 2023-10-15 |
| 431 | Human-in-the-loop Machine Translation with Large Language Model Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we propose a human-in-the-loop pipeline that guides LLMs to produce customized outputs with revision instructions. |
Xinyi Yang; Runzhe Zhan; Derek F. Wong; Junchao Wu; Lidia S. Chao; | arxiv-cs.CL | 2023-10-13 |
| 432 | Political Claim Identification and Categorization in A Multilingual Setting: First Experiments Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper explores different strategies for the cross-lingual projection of political claims analysis. |
Urs Zaberer; Sebastian Padó; Gabriella Lapesa; | arxiv-cs.CL | 2023-10-13 |
| 433 | XDial-Eval: A Multilingual Open-Domain Dialogue Evaluation Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To address the issue, we introduce xDial-Eval, built on top of open-source English dialogue evaluation datasets. |
CHEN ZHANG et. al. | arxiv-cs.CL | 2023-10-13 |
| 434 | Enhancing Expressivity Transfer in Textless Speech-to-speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Expressivity plays a vital role in conveying emotions, nuances, and cultural subtleties, thereby enhancing communication across diverse languages. To address this issue this study presents a novel method that operates at the discrete speech unit level and leverages multilingual emotion embeddings to capture language-agnostic information. |
Jarod Duret; Benjamin O’Brien; Yannick Estève; Titouan Parcollet; | arxiv-cs.SD | 2023-10-11 |
| 435 | Task-Oriented Semantic Communications for Speech Transmission Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Semantic communications execute intelligent tasks at the receiver by only transmitting necessary information. In this paper, we introduce TOS-ST, a task-oriented semantic … |
Zhenzi Weng; Zhijin Qin; Xiaoming Tao; | 2023 IEEE 98th Vehicular Technology Conference … | 2023-10-10 |
| 436 | Larth: Dataset and Machine Translation for Etruscan Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To the best of our knowledge, there are no publicly available Etruscan corpora for natural language processing. Therefore, we propose a dataset for machine translation from Etruscan to English, which contains 2891 translated examples from existing academic sources. |
Gianluca Vico; Gerasimos Spanakis; | arxiv-cs.CL | 2023-10-09 |
| 437 | All Translation Tools Are Not Equal: Investigating The Quality of Language Translation for Forced Migration Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: As the volume and complexity of forced movement continues to grow, there is an urgent need to use new data sources to better understand emerging crises. Organic sources, like … |
AMEETA AGRAWAL et. al. | 2023 IEEE 10th International Conference on Data Science and … | 2023-10-09 |
| 438 | Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Alternatively, we leverage a large language model to refine a hypothesis by providing it with terminology constraints. |
Nikolay Bogoychev; Pinzhen Chen; | arxiv-cs.CL | 2023-10-09 |
| 439 | Synslator: An Interactive Machine Translation Tool with Online Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces Synslator, a user-friendly computer-aided translation (CAT) tool that not only supports IMT, but is adept at online learning with real-time translation memories. |
JIAYI WANG et. al. | arxiv-cs.CL | 2023-10-08 |
| 440 | CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We develop multilingual modeling approaches for code translation and demonstrate their great potential in improving the translation quality of both low-resource and high-resource language pairs and boosting the training efficiency. |
Weixiang Yan; Yuchen Tian; Yunzhe Li; Qian Chen; Wen Wang; | arxiv-cs.AI | 2023-10-07 |
| 441 | Evaluation of Cross-Lingual Bug Localization: Two Industrial Cases Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study reports the results of applying the cross-lingual bug localization approach proposed by Xia et al. to industrial software projects. |
Shinpei Hayashi; Takashi Kobayashi; Tadahisa Kato; | arxiv-cs.SE | 2023-10-03 |
| 442 | Tuning Large Language Model for End-to-end Speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces LST, a Large multimodal model designed to excel at the E2E-ST task. |
HAO ZHANG et. al. | arxiv-cs.CL | 2023-10-03 |
| 443 | Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To understand when and why the navigation capabilities of language IDs are weakened, we compare two extreme decoder input cases in the ZST directions: Off-Target (OFF) and On-Target (ON) cases. |
CHANGTONG ZAN et. al. | arxiv-cs.CL | 2023-09-28 |
| 444 | MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Nonetheless, visual speech is not as distinguishable as audio speech, making it difficult to develop a mapping from source speech phonemes to the target language text. To address this issue, we propose MixSpeech, a cross-modality self-learning framework that utilizes audio speech to regularize the training of visual speech tasks. |
XIZE CHENG et. al. | iccv | 2023-09-27 |
| 445 | CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, these are not directly applicable to MMT since they do not provide aligned multimodal multilingual features for generative tasks. To alleviate this issue, instead of designing complex modules for MMT, we propose CLIPTrans, which simply adapts the independently pre-trained multimodal M-CLIP and the multilingual mBART. |
DEVAANSH GUPTA et. al. | iccv | 2023-09-27 |
| 446 | Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper describes the FBK’s participation in the Simultaneous Translation and Automatic Subtitling tracks of the IWSLT 2023 Evaluation Campaign. |
Sara Papi; Marco Gaido; Matteo Negri; | arxiv-cs.CL | 2023-09-27 |
| 447 | Segmentation-Free Streaming Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until the translation has been generated. |
Javier Iranzo-Sánchez; Jorge Iranzo-Sánchez; Adrià Giménez; Jorge Civera; Alfons Juan; | arxiv-cs.CL | 2023-09-26 |
| 448 | Hindi to English: Transformer-Based Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we have developed a Neural Machine Translation (NMT) system by training the Transformer model to translate texts from Indian Language Hindi to English. |
Kavit Gangar; Hardik Ruparel; Shreyas Lele; | arxiv-cs.CL | 2023-09-22 |
| 449 | Audience-specific Explanations for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we explore techniques to extract example explanations from a parallel corpus. |
Renhan Lou; Jan Niehues; | arxiv-cs.CL | 2023-09-22 |
| 450 | Domain Adaptation for Arabic Machine Translation: The Case of Financial Texts Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we developed carefully a parallel corpus for Arabic-English (AR- EN) translation in the financial domain for benchmarking different domain adaptation methods. |
Emad A. Alghamdi; Jezia Zakraoui; Fares A. Abanmy; | arxiv-cs.CL | 2023-09-22 |
| 451 | OSN-MDAD: Machine Translation Dataset for Arabic Multi-Dialectal Conversations on Online Social Media Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While few attempts have been made to build translation datasets for dialectal Arabic, they are domain dependent and are not OSN cultural-language friendly. In this work, we attempt to alleviate these limitations by proposing an online social network-based multidialect Arabic dataset that is crafted by contextually translating English tweets into four Arabic dialects: Gulf, Yemeni, Iraqi, and Levantine. |
Fatimah Alzamzami; Abdulmotaleb El Saddik; | arxiv-cs.CL | 2023-09-21 |
| 452 | SpeechAlign: A Framework for Speech Translation Alignment Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Speech-to-Speech and Speech-to-Text translation are currently dynamic areas of research. In our commitment to advance these fields, we present SpeechAlign, a framework designed to evaluate the underexplored field of source-target alignment in speech models. |
Belen Alastruey; Aleix Sant; Gerard I. Gállego; David Dale; Marta R. Costa-jussà; | arxiv-cs.CL | 2023-09-20 |
| 453 | Machine Translation of Electrical Terminology Constraints Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: In practical applications, the accuracy of domain terminology translation is an important criterion for the performance evaluation of domain machine translation models. Aiming at … |
Zepeng Wang; Yuan Chen; Juwei Zhang; | Inf. | 2023-09-20 |
| 454 | SignBank+: Preparing A Multilingual Sign Language Dataset for Machine Translation Using Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce SignBank+, a clean version of the SignBank dataset, optimized for machine translation between spoken language text and SignWriting, a phonetic sign language writing system. |
Amit Moryossef; Zifan Jiang; | arxiv-cs.CL | 2023-09-20 |
| 455 | NSOAMT — New Search Only Approach to Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The idea is to develop a solution that, by indexing an incremental set of words that combine a certain semantic meaning, makes it possible to create a process of correspondence between their native language record and the language of translation. |
João Luís; Diogo Cardoso; José Marques; Luís Campos; | arxiv-cs.CL | 2023-09-19 |
| 456 | LoGenText-Plus: Improving Neural Machine Translation-based Logging Texts Generation with Syntactic Templates Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Developers insert logging statements in the source code to collect important runtime information about software systems. The textual descriptions in logging statements (i.e., … |
Zishuo Ding; Yiming Tang; Xiaoyu Cheng; Heng Li; Weiyi Shang; | ACM Transactions on Software Engineering and Methodology | 2023-09-18 |
| 457 | Optimizing Machine Translation for Virtual Assistants: Multi-Variant Generation with VerbNet and Conditional Beam Search Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: In this paper, we introduce a domain-adapted machine translation (MT) model for intelligent virtual assistants (IVA) designed to translate natural language understanding (NLU) … |
Marcin Sowański; Artur Janicki; | 2023 18th Conference on Computer Science and Intelligence … | 2023-09-17 |
| 458 | Controllability for English-Ukrainian Machine Translation By Using Style Transfer Techniques Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: While straightforward machine translation got significant improvements in the last 10 years with the arrival of encoder-decoder neural networks and transformers architecture, … |
DANIIL MAKSYMENKO et. al. | 2023 18th Conference on Computer Science and Intelligence … | 2023-09-17 |
| 459 | Use of Neural Machine Translation in Multimodal Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Multimodal Neural Machine Translation (MNMT) is a type of Machine Translation that allows the translation of source language that contains various forms of information, such as … |
Manavi Nair; Sarvesh Tanwar; Sumit Badotra; Vinay Kukreja; | 2023 6th International Conference on Contemporary Computing … | 2023-09-14 |
| 460 | Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Hallucinations and off-target translation remain unsolved problems in MT, especially for low-resource languages and massively multilingual models. In this paper, we introduce two related methods to mitigate these failure cases with a modified decoding objective, without either requiring retraining or external models. |
Rico Sennrich; Jannis Vamvas; Alireza Mohammadshahi; | arxiv-cs.CL | 2023-09-13 |
| 461 | Dual-view Curricular Optimal Transport for Cross-lingual Cross-modal Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Improperly assuming the pseudo-parallel data are correctly correlated will make the networks overfit to the noisy correspondence. Therefore, we propose Dual-view Curricular Optimal Transport (DCOT) to learn with noisy correspondence in CCR. |
YABING WANG et. al. | arxiv-cs.CV | 2023-09-11 |
| 462 | The Effect of Alignment Objectives on Code-Switching Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we are proposing a way of training a single machine translation model that is able to translate monolingual sentences from one language to another, along with translating code-switched sentences to either language. |
Mohamed Anwar; | arxiv-cs.CL | 2023-09-10 |
| 463 | Algorithmic Translation Correction Mechanisms: An End-to-end Algorithmic Implementation of English-Chinese Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: INTRODUCTION: Machine translation is a modern natural language processing research field with important scientific and practical significance. In practice, the variation of … |
Lei Shi; | EAI Endorsed Trans. Scalable Inf. Syst. | 2023-09-05 |
| 464 | Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a novel approach Epi-Curriculum to address low-resource domain adaptation (DA), which contains a new episodic training framework along with denoised curriculum learning. |
Keyu Chen; Di Zhuang; Mingchen Li; J. Morris Chang; | arxiv-cs.LG | 2023-09-05 |
| 465 | Advancing Text-to-GLOSS Neural Translation Using A Novel Hyper-parameter Optimization Technique Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we investigate the use of transformers for Neural Machine Translation of text-to-GLOSS for Deaf and Hard-of-Hearing communication. |
Younes Ouargani; Noussaima El Khattabi; | arxiv-cs.CL | 2023-09-05 |
| 466 | Exploration of Low-resource Language-oriented Machine Translation System of Genetic Algorithm-optimized Hyper-task Network Under Cloud Platform Technology Related Papers Related Patents Related Grants Related Venues Related Experts View |
Xiao Liu; Junlong Chen; Deyu Qi; Tong Zhang; | J. Supercomput. | 2023-09-04 |
| 467 | Neural Machine Translation Systems for English to Khasi: A Case Study of An Austroasiatic Language Related Papers Related Patents Related Grants Related Venues Related Experts View |
A. V. Hujon; Thoudam Doren Singh; Khwairakpam Amitab; | Expert Syst. Appl. | 2023-09-01 |
| 468 | Impact of Visual Context on Noisy Multimodal NMT: An Empirical Study for English to Indian Languages Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: The study investigates the effectiveness of utilizing multimodal information in Neural Machine Translation (NMT). |
Baban Gain; Dibyanayan Bandyopadhyay; Samrat Mukherjee; Chandranath Adak; Asif Ekbal; | arxiv-cs.CL | 2023-08-30 |
| 469 | Training and Meta-Evaluating Machine Translation Evaluation Metrics at The Paragraph Level Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: As research on machine translation moves to translating text beyond the sentence level, it remains unclear how effective automatic evaluation metrics are at scoring longer … |
Daniel Deutsch; Juraj Juraska; Mara Finkelstein; Markus Freitag; | arxiv-cs.CL | 2023-08-25 |
| 470 | Improving Translation Faithfulness of Large Language Models Via Augmenting Instructions IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Large Language Models (LLMs) present strong general capabilities, and a current compelling challenge is stimulating their specialized capabilities, such as machine translation, through low-cost instruction tuning. |
YIJIE CHEN et. al. | arxiv-cs.CL | 2023-08-24 |
| 471 | SeamlessM4T: Massively Multilingual & Multimodal Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: More specifically, conventional speech-to-speech translation systems rely on cascaded systems that perform translation progressively, putting high-performing unified systems out of reach. To address these gaps, we introduce SeamlessM4T, a single model that supports speech-to-speech translation, speech-to-text translation, text-to-speech translation, text-to-text translation, and automatic speech recognition for up to 100 languages. |
SEAMLESS COMMUNICATION et. al. | arxiv-cs.CL | 2023-08-22 |
| 472 | An Effective Method Using Phrase Mechanism in Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we report an effective method using a phrase mechanism, PhraseTransformer, to improve the strong baseline model Transformer in constructing a Neural Machine Translation (NMT) system for parallel corpora Vietnamese-Chinese. |
Phuong Minh Nguyen; Le Minh Nguyen; | arxiv-cs.CL | 2023-08-21 |
| 473 | Knowledge Distillation on Joint Task End-to-End Speech Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: An End-to-End Speech Translation (E2E-ST) model takes input audio in one language and directly produces output text in another language. The model requires to learn both … |
Khandokar Md. Nayem; Ran Xue; Ching-Yun Chang; A. Shanbhogue; | Interspeech | 2023-08-20 |
| 474 | Factuality Detection Using Machine Translation — A Use Case for German Clinical Text Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In the context of factuality detection, this work presents a simple solution using machine translation to translate English data to German to train a transformer-based factuality detection model. |
Mohammed Bin Sumait; Aleksandra Gabryszak; Leonhard Hennig; Roland Roller; | arxiv-cs.CL | 2023-08-17 |
| 475 | Fast Training of NMT Model with Data Sorting Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: One potential area for improvement is to address the computation of empty tokens that the Transformer computes only to discard them later, leading to an unnecessary computational burden. To tackle this, we propose an algorithm that sorts translation sentence pairs based on their length before batching, minimizing the waste of computing power. |
Daniela N. Rim; Kimera Richard; Heeyoul Choi; | arxiv-cs.CL | 2023-08-16 |
| 476 | VBD-MT Chinese-Vietnamese Translation Systems for VLSP 2022 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present our systems participated in the VLSP 2022 machine translation shared task. |
Hai Long Trieu; Song Kiet Bui; Tan Minh Tran; Van Khanh Tran; Hai An Nguyen; | arxiv-cs.CL | 2023-08-15 |
| 477 | Extrapolating Large Language Models to Non-English By Aligning Languages IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we empower pre-trained LLMs on non-English languages by building semantic alignment across languages. |
WENHAO ZHU et. al. | arxiv-cs.CL | 2023-08-09 |
| 478 | Negative Lexical Constraints in Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We compared various methods based on modifying either the decoding process or the training data. |
Josef Jon; Dušan Variš; Michal Novák; João Paulo Aires; Ondřej Bojar; | arxiv-cs.CL | 2023-08-07 |
| 479 | Show Me The World in My Language: Establishing The First Baseline for Scene-Text to Scene-Text Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we study the task of “visually” translating scene text from a source language (e.g., Hindi) to a target language (e.g., English). |
Shreyas Vaidya; Arvind Kumar Sharma; Prajwal Gatti; Anand Mishra; | arxiv-cs.CV | 2023-08-06 |
| 480 | Do Multilingual Language Models Think Better in English? IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we introduce a new approach called self-translate, which overcomes the need of an external translation system by leveraging the few-shot translation capabilities of multilingual language models. |
Julen Etxaniz; Gorka Azkune; Aitor Soroa; Oier Lopez de Lacalle; Mikel Artetxe; | arxiv-cs.CL | 2023-08-02 |
| 481 | Predicting Perfect Quality Segments in MT Output with Fine-Tuned OpenAI LLM: Is It Possible to Capture Editing Distance Patterns from Historical Data? Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Translation Quality Estimation (TQE) is an essential step before deploying the output translation into usage. TQE is also critical in assessing machine translation (MT) and human … |
Serge Gladkoff; G. Erofeev; Lifeng Han; G. Nenadic; | ArXiv | 2023-07-31 |
| 482 | MTUncertainty: Assessing The Need for Post-editing of Machine Translation Outputs By Fine-tuning OpenAI LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We take OpenAI models as the best state-of-the-art technology and approach TQE as a binary classification task. |
Serge Gladkoff; Lifeng Han; Gleb Erofeev; Irina Sorokina; Goran Nenadic; | arxiv-cs.CL | 2023-07-31 |
| 483 | Structural Transfer Learning in NL-to-Bash Semantic Parsers Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a methodology for obtaining a quantitative understanding of structural overlap between machine translation tasks. |
Kyle Duffy; Satwik Bhattamishra; Phil Blunsom; | arxiv-cs.CL | 2023-07-31 |
| 484 | Toward Quantum Machine Translation of Syntactically Distinct Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The present study aims to explore the feasibility of language translation using quantum natural language processing algorithms on noisy intermediate-scale quantum (NISQ) devices. |
Mina Abbaszade; Mariam Zomorodi; Vahid Salari; Philip Kurian; | arxiv-cs.CL | 2023-07-31 |
| 485 | Using Online Machine Translation in International Scholarly Writing and Publishing: A Longitudinal Case of A Chinese Engineering Scholar Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Scholars who use English as an additional language (EAL) worldwide are under increasing pressure to write and publish in English due to the pervasive publish‐or‐perish culture and … |
C. Zou; Wei Gong; Ping Li; | Learned Publishing | 2023-07-31 |
| 486 | Multilingual Lexical Simplification Via Paraphrase Generation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a novel multilingual LS method via paraphrase generation, as paraphrases provide diversity in word selection while preserving the sentence’s meaning. |
KANG LIU et. al. | arxiv-cs.CL | 2023-07-27 |
| 487 | XDLM: Cross-lingual Diffusion Language Model for Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Additionally, while pretraining with diffusion models has been studied within a single language, the potential of cross-lingual pretraining remains understudied. To address these gaps, we propose XDLM, a novel Cross-lingual diffusion model for machine translation, consisting of pretraining and fine-tuning stages. |
Linyao Chen; Aosong Feng; Boming Yang; Zihui Li; | arxiv-cs.CL | 2023-07-25 |
| 488 | Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present a comprehensive study on the robustness of current text adversarial attacks to round-trip translation. |
Neel Bhandari; Pin-Yu Chen; | arxiv-cs.CL | 2023-07-24 |
| 489 | Incorporating Human Translator Style Into English-Turkish Literary Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we focus on English-Turkish literary translation and develop machine translation models that take into account the stylistic features of translators. |
ZEYNEP YIRMIBEŞOĞLU et. al. | arxiv-cs.CL | 2023-07-21 |
| 490 | Construction of Mizo: English Parallel Corpus for Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Parallel corpus is a key component of statistical and Neural Machine Translation (NMT). While most research focuses on machine translation, corpus creation studies are limited for … |
Thangkhanhau Haulai; J. Hussain; | ACM Transactions on Asian and Low-Resource Language … | 2023-07-21 |
| 491 | Improving End-to-End Speech Translation By Imitation-Based Knowledge Distillation with Synthetic Transcripts Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present an imitation learning approach where a teacher NMT system corrects the errors of an AST student without relying on manual transcripts. |
Rebekka Hubert; Artem Sokolov; Stefan Riezler; | arxiv-cs.CL | 2023-07-17 |
| 492 | Data Augmentation for Machine Translation Via Dependency Subtree Swapping Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present a generic framework for data augmentation via dependency subtree swapping that is applicable to machine translation. |
Attila Nagy; Dorina Petra Lakatos; Botond Barta; Patrick Nanys; Judit Ács; | arxiv-cs.CL | 2023-07-13 |
| 493 | Investigating Unsupervised Neural Machine Translation for Low-resource Language Pair English-Mizo Via Lexically Enhanced Pre-trained Language Models Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The vast majority of languages in the world at present are considered to be low-resource languages. Since the availability of large parallel data is crucial for the success of … |
C. Lalrempuii; B. Soni; | ACM Transactions on Asian and Low-Resource Language … | 2023-07-13 |
| 494 | Back Deduction Based Testing for Word Sense Disambiguation Ability of Machine Translation Systems Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Machine translation systems have penetrated our daily lives, providing translation services from source language to target language to millions of users online daily. Word Sense … |
JUN WANG et. al. | Proceedings of the 32nd ACM SIGSOFT International Symposium … | 2023-07-12 |
| 495 | The NPU-MSXF Speech-to-Speech Translation System for IWSLT 2023 Speech-to-Speech Translation Task Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes the NPU-MSXF system for the IWSLT 2023 speech-to-speech translation (S2ST) task which aims to translate from English speech of multi-source to Chinese speech. |
KUN SONG et. al. | arxiv-cs.SD | 2023-07-10 |
| 496 | Multi-VALUE: A Framework for Cross-Dialectal English NLP IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a suite of resources for evaluating and achieving English dialect invariance. |
CALEB ZIEMS et. al. | acl | 2023-07-08 |
| 497 | TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present a parallel tense test set, containing French-English 552 utterances. |
Yiming Ai; Zhiwei He; Kai Yu; Rui Wang; | acl | 2023-07-08 |
| 498 | Simple and Effective Unsupervised Speech Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue, we study a simple and effective approach to build speech translation systems without labeled data by leveraging recent advances in unsupervised speech recognition, machine translation and speech synthesis, either in a pipeline approach, or to generate pseudo-labels for training end-to-end speech translation models. |
CHANGHAN WANG et. al. | acl | 2023-07-08 |
| 499 | Back Translation for Speech-to-text Translation Without Transcripts IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we aim to utilize large amounts of target-side monolingual data to enhance ST without transcripts. |
Qingkai Fang; Yang Feng; | acl | 2023-07-08 |
| 500 | Learning Optimal Policy for Simultaneous Machine Translation Via Binary Search IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present a new method for constructing the optimal policy online via binary search. |
Shoutao Guo; Shaolei Zhang; Yang Feng; | acl | 2023-07-08 |
| 501 | PEIT: Bridging The Modality Gap with Pre-trained Models for End-to-End Image Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose PEIT, an end-to-end image translation framework that bridges the modality gap with pre-trained models. |
Shaolin Zhu; Shangjie Li; Yikun Lei; Deyi Xiong; | acl | 2023-07-08 |
| 502 | Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a simple yet efficient approach to adapt VLP to unseen languages using MPLM. |
Yasmine Karoui; R�mi Lebret; Negar Foroutan Eghlidi; Karl Aberer; | acl | 2023-07-08 |
| 503 | MCLIP: Multilingual CLIP Via Cross-lingual Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce mCLIP, a retrieval-efficient dual-stream multilingual VLP model, trained by aligning the CLIP model and a Multilingual Text Encoder (MTE) through a novel Triangle Cross-modal Knowledge Distillation (TriKD) method. |
GUANHUA CHEN et. al. | acl | 2023-07-08 |
| 504 | Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Firstly, the current objective of KD spreads its focus to whole distributions to learn the knowledge, yet lacks special treatment on the most crucial top-1 information. Secondly, the knowledge is largely covered by the golden information due to the fact that most top-1 predictions of teachers overlap with ground-truth tokens, which further restricts the potential of KD. To address these issues, we propose a new method named Top-1 Information Enhanced Knowledge Distillation (TIE-KD). |
SONGMING ZHANG et. al. | acl | 2023-07-08 |
| 505 | What About �em�? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Wrong pronoun translations can discriminate against marginalized groups, e. g. , non-binary individuals (Dev et al. , 2021). In this �reality check�, we study how three commercial MT systems translate 3rd-person pronouns. |
Anne Lauscher; Debora Nozza; Ehm Miltersen; Archie Crowley; Dirk Hovy; | acl | 2023-07-08 |
| 506 | Understanding and Bridging The Modality Gap for Speech Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We find that the modality gap is relatively small during training except for some difficult cases, but keeps increasing during inference due to the cascading effect. To address these problems, we propose the Cross-modal Regularization with Scheduled Sampling (Cress) method. |
Qingkai Fang; Yang Feng; | acl | 2023-07-08 |
| 507 | Easy Guided Decoding in Providing Suggestions for Interactive Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we utilize the parameterized objective function of neural machine translation (NMT) and propose a novel constrained decoding algorithm, namely Prefix-Suffix Guided Decoding (PSGD), to deal with the TS problem without additional training. |
Ke Wang; Xin Ge; Jiayi Wang; Yuqi Zhang; Yu Zhao; | acl | 2023-07-08 |
| 508 | RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While ACT has garnered attention in recent years due to its usefulness in real-world applications, progress in the task is currently limited by dataset availability, since most prior approaches rely on supervised methods. To address this limitation, we propose Retrieval and Attribute-Marking enhanced Prompting (RAMP), which leverages large multilingual language models to perform ACT in few-shot and zero-shot settings. |
GABRIELE SARTI et. al. | acl | 2023-07-08 |
| 509 | CMOT: Cross-modal Mixup Via Optimal Transport for Speech Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose Cross-modal Mixup via Optimal Transport (CMOT) to overcome the modality gap. |
Yan Zhou; Qingkai Fang; Yang Feng; | acl | 2023-07-08 |
| 510 | Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To eliminate the rule-based nature of data creation, we instead propose using machine translation models to create gender-biased text from real gender-fair text via round-trip translation. |
Chantal Amrhein; Florian Schottmann; Rico Sennrich; Samuel L�ubli; | acl | 2023-07-08 |
| 511 | Do GPTs Produce Less Literal Translations? IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, there has been relatively little investigation on how such translations differ qualitatively from the translations generated by standard Neural Machine Translation (NMT) models. In this work, we investigate these differences in terms of the literalness of translations produced by the two systems. |
Vikas Raunak; Arul Menezes; Matt Post; Hany Hassan; | acl | 2023-07-08 |
| 512 | Translation-Enhanced Multilingual Text-to-Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We provide two key contributions. 1) Relying on a multilingual multi-modal encoder, we provide a systematic empirical study of standard methods used in cross-lingual NLP when applied to mTTI: Translate Train, Translate Test, and Zero-Shot Transfer. 2) We propose Ensemble Adapter (EnsAd), a novel parameter-efficient approach that learns to weigh and consolidate the multilingual text knowledge within the mTTI framework, mitigating the language gap and thus improving mTTI performance. |
Yaoyiran Li; Ching-Yun Chang; Stephen Rawls; Ivan Vulic; Anna Korhonen; | acl | 2023-07-08 |
| 513 | Scene Graph As Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text image pairs, and tested with only source-text inputs. |
Hao Fei; Qian Liu; Meishan Zhang; Min Zhang; Tat-Seng Chua; | acl | 2023-07-08 |
| 514 | A Simple Concatenation Can Effectively Improve Speech Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Inspired by the works of video Transformer, we propose a simple unified cross-modal ST method, which concatenates speech and text as the input, and builds a teacher that can utilize both cross-modal information simultaneously. |
Linlin Zhang; Kai Fan; Boxing Chen; Luo Si; | acl | 2023-07-08 |
| 515 | Searching for Needles in A Haystack: On The Role of Incidental Bilingualism in PaLM�s Translation Capability Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a mixed-method approach to measure and understand incidental bilingualism at scale. |
Eleftheria Briakou; Colin Cherry; George Foster; | acl | 2023-07-08 |
| 516 | Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Unpaired cross-lingual image captioning has long suffered from irrelevancy and disfluency issues, due to the inconsistencies of the semantic scene and syntax attributes during transfer. In this work, we propose to address the above problems by incorporating the scene graph (SG) structures and the syntactic constituency (SC) trees. |
Shengqiong Wu; Hao Fei; Wei Ji; Tat-Seng Chua; | acl | 2023-07-08 |
| 517 | XPQA: Cross-Lingual Product Question Answering in 12 Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While existing work on PQA focuses mainly on English, in practice there is need to support multiple customer languages while leveraging product information available in English. To study this practical industrial task, we present xPQA, a large-scale annotated cross-lingual PQA dataset in 12 languages, and report results in (1) candidate ranking, to select the best English candidate containing the information to answer a non-English question; and (2) answer generation, to generate a natural-sounding non-English answer based on the selected English candidate. |
Xiaoyu Shen; Akari Asai; Bill Byrne; Adria De Gispert; | acl | 2023-07-08 |
| 518 | On Evaluating Multilingual Compositional Generalization with Translated Datasets Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, we show that this entails critical semantic distortion. To address this limitation, we craft a faithful rule-based translation of the MCWQ dataset from English to Chinese and Japanese. |
Zi Wang; Daniel Hershcovich; | acl | 2023-07-08 |
| 519 | Subset Retrieval Nearest Neighbor Machine Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose �Subset kNN-MT�, which improves the decoding speed of kNN-MT by two methods: (1) retrieving neighbor target tokens from a subset that is the set of neighbor sentences of the input sentence, not from all sentences, and (2) efficient distance computation technique that is suitable for subset neighbor search using a look-up table. |
HIROYUKI DEGUCHI et. al. | acl | 2023-07-08 |
| 520 | Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present a new MMT approach based on a strong text-only MT model, which uses neural adapters, a novel guided self-attention mechanism and which is jointly trained on both visually-conditioned masking and MMT. |
Matthieu Futeral; Cordelia Schmid; Ivan Laptev; Beno�t Sagot; Rachel Bawden; | acl | 2023-07-08 |
| 521 | Neural Machine Translation Methods for Translating Text to Sign Language Glosses IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our experiments, we improve the performance of the transformer-based models via (1) data augmentation, (2) semi-supervised Neural Machine Translation (NMT), (3) transfer learning and (4) multilingual NMT. |
Dele Zhu; Vera Czehmann; Eleftherios Avramidis; | acl | 2023-07-08 |
| 522 | Understanding and Improving The Robustness of Terminology Constraints in Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we study the robustness of two typical terminology translation methods: Placeholder (PH) and Code-Switch (CS), concerning (1) the number of constraints and (2) the target constraint length. |
HUAAO ZHANG et. al. | acl | 2023-07-08 |
| 523 | Exploring Better Text Image Translation with Multimodal Codebook Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we first annotate a Chinese-English TIT dataset named OCRMT30K, providing convenience for subsequent studies. |
ZHIBIN LAN et. al. | acl | 2023-07-08 |
| 524 | Continual Knowledge Distillation for Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a method called continual knowledge distillation to take advantage of existing translation models to improve one model of interest. |
Yuanchi Zhang; Peng Li; Maosong Sun; Yang Liu; | acl | 2023-07-08 |
| 525 | Extrinsic Evaluation of Machine Translation Metrics IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we investigate how useful MT metrics are at detecting the segment-level quality by correlating metrics with how useful the translations are for downstream task. |
Nikita Moghe; Tom Sherborne; Mark Steedman; Alexandra Birch; | acl | 2023-07-08 |
| 526 | Learning Language-Specific Layers for Multilingual Machine Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce Language-Specific Transformer Layers (LSLs), which allow us to increase model capacity, while keeping the amount of computation and the number of parameters used in the forward pass constant. |
Telmo Pires; Robin Schmidt; Yi-Hsiu Liao; Stephan Peitz; | acl | 2023-07-08 |
| 527 | Songs Across Borders: Singable and Controllable Neural Lyric Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper bridges the singability quality gap by formalizing lyric translation into a constrained translation problem, converting theoretical guidance and practical techniques from translatology literature to prompt-driven NMT approaches, exploring better adaptation methods, and instantiating them to an English-Chinese lyric translation system. |
Longshen Ou; Xichu Ma; Min-Yen Kan; Ye Wang; | acl | 2023-07-08 |
| 528 | Using Neural Machine Translation for Generating Diverse Challenging Exercises for Language Learner Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel approach to automatically generate distractors for cloze exercises for English language learners, using round-trip neural machine translation. |
Frank Palma Gomez; Subhadarshi Panda; Michael Flor; Alla Rozovskaya; | acl | 2023-07-08 |
| 529 | Neural Machine Translation for Mathematical Formulae Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we perform the tasks of translating from LaTeX to Mathematica as well as from LaTeX to semantic LaTeX. |
Felix Petersen; Moritz Schubotz; Andre Greiner-Petter; Bela Gipp; | acl | 2023-07-08 |
| 530 | Text Style Transfer Back-Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: For natural inputs, BT brings only slight improvements and sometimes even adverse effects. To address this issue, we propose Text Style Transfer Back Translation (TST BT), which uses a style transfer to modify the source side of BT data. |
DAIMENG WEI et. al. | acl | 2023-07-08 |
| 531 | INK: Injecting KNN Knowledge in Nearest Neighbor Machine Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose an effective training framework INK to directly smooth the representation space via adjusting representations of kNN neighbors with a small number of new parameters. |
Wenhao Zhu; Jingjing Xu; Shujian Huang; Lingpeng Kong; Jiajun Chen; | acl | 2023-07-08 |
| 532 | MultiTACRED: A Multilingual Version of The TAC Relation Extraction Dataset Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Relation extraction (RE) is a fundamental task in information extraction, whose extension to multilingual settings has been hindered by the lack of supervised resources comparable in size to large English datasets such as TACRED (Zhang et al. , 2017). To address this gap, we introduce the MultiTACRED dataset, covering 12 typologically diverse languages from 9 language families, which is created by machine-translating TACRED instances and automatically projecting their entity annotations. |
Leonhard Hennig; Philippe Thomas; Sebastian M�ller; | acl | 2023-07-08 |
| 533 | An Analysis of Error Types in Chinese to English Translation By Google Neural Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Abstract: Due to the rapid development of globalization and digitalization, neural machine translation (NMT) systems have gradually developed into the mainstream technology in the … |
Yanqi Lu; | Proceedings of the 2023 International Joint Conference on … | 2023-07-07 |
| 534 | Performance Evaluation of English to Bodo Neural Machine Translation System with Varying Model Architecture and Vocabulary Size Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper is about a work done on Neural Machine Translation of English-Bodo language pair using deep learning technique. Bodo is a language of northeastern part of India … |
P. Boruah; Shikhar Kr. Sarma; Kishore Kashyap; Simanta Kalita; | 2023 14th International Conference on Computing … | 2023-07-06 |
| 535 | Tokenization Effect on Neural Machine Translation: An Experimental Investigation for English-Assamese Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Tokenization, as a research task, is mostly overlooked when dealing with machine translation as much emphasis is placed on modelling or data enhancement, not to speak for language … |
Mazida Akhtara Ahmed; Kishore Kashyap; Shikhar Kumar Sarma; | 2023 14th International Conference on Computing … | 2023-07-06 |
| 536 | To Be or Not to Be: A Translation Reception Study of A Literary Text Translated Into Dutch and Catalan Using Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This article presents the results of a study involving the reception of a fictional story by Kurt Vonnegut translated from English into Catalan and Dutch in three conditions: machine-translated (MT), post-edited (PE) and translated from scratch (HT). |
Ana Guerberof Arenas; Antonio Toral; | arxiv-cs.CL | 2023-07-05 |
| 537 | Simplification of Arabic Text: A Hybrid Approach Integrating Machine Translation and Transformer-based Lexical Model Related Papers Related Patents Related Grants Related Venues Related Experts View |
Suha Al-Thanyyan; Aqil M. Azmi; | J. King Saud Univ. Comput. Inf. Sci. | 2023-07-01 |
| 538 | X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Task-oriented dialogue research has mainly focused on a few popular languages like English and Chinese, due to the high dataset creation cost for a new language. |
MEHRAD MORADSHAHI et. al. | arxiv-cs.CL | 2023-06-30 |
| 539 | Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a simple yet efficient approach to adapt VLP to unseen languages using MPLM. |
Yasmine Karoui; Rémi Lebret; Negar Foroutan; Karl Aberer; | arxiv-cs.CL | 2023-06-29 |
| 540 | Learning Multilingual Expressive Speech Representation for Prosody Prediction Without Parallel Data Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: We propose a method for speech-to-speech emotionpreserving translation that operates at the level of discrete speech units. Our approach relies on the use of multilingual emotion … |
J. Duret; Titouan Parcollet; Y. Estève; | ArXiv | 2023-06-29 |
| 541 | The Unreasonable Effectiveness of Few-shot Learning for Machine Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show that with only 5 examples of high-quality translation data shown at inference, a transformer decoder-only model trained solely with self-supervised learning, is able to match specialized supervised state-of-the-art models as well as more general commercial translation systems. |
XAVIER GARCIA et. al. | icml | 2023-06-27 |
| 542 | Slot Lost in Translation? Not Anymore: A Machine Translation Model for Virtual Assistants with Type-Independent Slot Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: In this article, we present a machine translation model adapted to the domain of intelligent virtual assistants (IVA) that can be used to translate training and evaluation … |
Marcin Sowanski; A. Janicki; | 2023 30th International Conference on Systems, Signals and … | 2023-06-27 |
| 543 | Quality Estimation of Machine Translated Texts Based on Direct Evidence from Training Data Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we show that the parallel corpus used as training data for training the MT system holds direct clues for estimating the quality of translations produced by the MT system. |
Vibhuti Kumari; Narayana Murthy Kavi; | arxiv-cs.CL | 2023-06-27 |
| 544 | Constructing Multilingual Code Search Dataset Using Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this research, we create a multilingual code search dataset in four natural and four programming languages using a neural machine translation model. |
Ryo Sekizawa; Nan Duan; Shuai Lu; Hitomi Yanaka; | arxiv-cs.CL | 2023-06-27 |
| 545 | Prompting Neural Machine Translation with Translation Memories Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a simple but effective method to introduce TMs into neural machine translation (NMT) systems. |
ABUDUREXITI REHEMAN et. al. | aaai | 2023-06-26 |
| 546 | A Graph Fusion Approach for Cross-Lingual Machine Reading Comprehension Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a novel approach, which jointly models the cross-lingual alignment information and the mono-lingual syntax information using a graph. |
ZENAN XU et. al. | aaai | 2023-06-26 |
| 547 | Evaluation of Chinese-English Machine Translation of Emotion-Loaded Microblog Texts: A Human Annotated Dataset for The Quality Assessment of Emotion Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we focus on how current Machine Translation (MT) tools perform on the translation of emotion-loaded texts by evaluating outputs from Google Translate according to a framework proposed in this paper. |
Shenbin Qian; Constantin Orasan; Felix do Carmo; Qiuliang Li; Diptesh Kanojia; | arxiv-cs.CL | 2023-06-20 |
| 548 | BayLing: Bridging Cross-lingual Alignment and Instruction Following Through Interactive Translation for Large Language Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To minimize human workload, we propose to transfer the capabilities of language generation and instruction following from English to other languages through an interactive translation task. |
SHAOLEI ZHANG et. al. | arxiv-cs.CL | 2023-06-19 |
| 549 | Data Augmentation Via Back-translation for Aspect Term Extraction Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: We tackle Aspect Term Extraction (ATE), a task that automatically recognizes aspect terms conditioned on the under-standing of word-level semantics. Due to the capacity of … |
Qingting Xu; Yu Hong; Jiaxiang Chen; Jianmin Yao; Guodong Zhou; | 2023 International Joint Conference on Neural Networks … | 2023-06-18 |
| 550 | Robust Secret Data Hiding for Transformer-based Neural Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Hiding secret information in text is a research area of significant importance and a great challenge. In recent years, there have been huge developments and exciting advances in … |
Tianhe Lu; Gongshen Liu; Ru Zhang; Peixuan Li; Tianjie Ju; | 2023 International Joint Conference on Neural Networks … | 2023-06-18 |
| 551 | Sheffield’s Submission to The AmericasNLP Shared Task on Machine Translation Into Indigenous Languages Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper we describe the University of Sheffield’s submission to the AmericasNLP 2023 Shared Task on Machine Translation into Indigenous Languages which comprises the translation from Spanish to eleven indigenous languages. |
Edward Gow-Smith; Danae Sánchez Villegas; | arxiv-cs.CL | 2023-06-16 |
| 552 | Discourse Representation Structure Parsing for Chinese Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We describe the pipeline of automatically collecting the linearized Chinese meaning representation data for sequential-to sequential neural networks. |
Chunliu Wang; Xiao Zhang; Johan Bos; | arxiv-cs.CL | 2023-06-16 |
| 553 | Baseline Transliteration Corpus for Improved English-Amharic Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View |
Yohannes Biadgligne; Kamel Smaïli; | Informatica (Slovenia) | 2023-06-15 |
| 554 | Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce Babel-ImageNet, a massively multilingual benchmark that offers (partial) translations of ImageNet labels to 100 languages, built without machine translation or manual annotation. |
Gregor Geigle; Radu Timofte; Goran Glavaš; | arxiv-cs.CL | 2023-06-14 |
| 555 | A Survey of Vision-Language Pre-training from The Lens of Multimodal Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We summarize the common architectures, pre-training objectives, and datasets from literature and conjecture what further is needed to make progress on multimodal machine translation. |
Jeremy Gwinnup; Kevin Duh; | arxiv-cs.CL | 2023-06-12 |
| 556 | Rethinking Translation Memory Augmented Neural Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: This paper rethinks translation memory augmented neural machine translation (TM-augmented NMT) from two perspectives, i.e., a probabilistic view of retrieval and the variance-bias … |
HONGKUN HAO et. al. | arxiv-cs.CL | 2023-06-12 |
| 557 | Textual Augmentation Techniques Applied to Low Resource Machine Translation: Case of Swahili Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we investigate the impact of applying textual data augmentation tasks to low resource machine translation. |
Catherine Gitau; VUkosi Marivate; | arxiv-cs.CL | 2023-06-12 |
| 558 | Measuring Sentiment Bias in Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we explore how machine translation might introduce a bias in sentiments as classified by sentiment analysis models. |
KAI HARTUNG et. al. | arxiv-cs.CL | 2023-06-12 |
| 559 | A Benchmark Dataset and Evaluation Methodology for Chinese Zero Pronoun Translation Related Papers Related Patents Related Grants Related Venues Related Experts View |
MINGZHOU XU et. al. | Language Resources and Evaluation | 2023-06-10 |
| 560 | Good, But Not Always Fair: An Evaluation of Gender Bias for Three Commercial Machine Translation Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Consequently, analyses have been redirected to more nuanced aspects, intricate phenomena, as well as potential risks that may arise from the widespread use of MT tools. Along this line, this paper offers a meticulous assessment of three commercial MT systems – Google Translate, DeepL, and Modern MT – with a specific focus on gender translation and bias. |
Silvia Alma Piazzolla; Beatrice Savoldi; Luisa Bentivogli; | arxiv-cs.CL | 2023-06-09 |
| 561 | Assisting Language Learners: Automated Trans-Lingual Definition Generation Via Contrastive Prompt Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a novel task of Trans-Lingual Definition Generation (TLDG), which aims to generate definitions in another language, i.e., the native speaker’s language. |
HENGYUAN ZHANG et. al. | arxiv-cs.CL | 2023-06-09 |
| 562 | Improving Language Model Integration for Neural Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Recently, some works on automatic speech recognition have demonstrated that, if the implicit language model is neutralized in decoding, further improvements can be gained when integrating an external language model. In this work, we transfer this concept to the task of machine translation and compare with the most prominent way of including additional monolingual data – namely back-translation. |
Christian Herold; Yingbo Gao; Mohammad Zeineldeen; Hermann Ney; | arxiv-cs.CL | 2023-06-08 |
| 563 | Twi Machine Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: French is a strategically and economically important language in the regions where the African language Twi is spoken. However, only a very small proportion of Twi speakers in … |
Frederick Gyasi; Tim Schlippe; | Big Data Cogn. Comput. | 2023-06-08 |
| 564 | A Little Is Enough: Few-Shot Quality Estimation Based Corpus Filtering Improves Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: All the scripts and datasets utilized in this study will be publicly available. |
Akshay Batheja; Pushpak Bhattacharyya; | arxiv-cs.CL | 2023-06-06 |
| 565 | MCTS: A Multi-Reference Chinese Text Simplification Dataset |