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.
Based in New York, Paper Digest is dedicated to helping people generate contents & reason over unstructured data. Different from black-box approaches, we build deep models on semantics, which allows results to be produced with explainations. Such models power this website, and are behind our services including “search engine”, “summarization”, “question answering”, and “literature review”.
If you do not want to miss interesting academic papers, you are welcome to sign up our free daily paper digest service to get updates on new papers published in your area every day. You are also welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
New York City, New York, 10017
team@paperdigest.org
TABLE 1: Paper Digest: Recent Papers on Machine Translation
| Paper | Author(s) | Source | Date | |
|---|---|---|---|---|
| 1 | Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, in one-tomany scenario, we propose a multilingual distillation method to make the new model (student) jointly learn multilingual output from old model (teacher) and new task. |
YANG ZHAO et. al. | arxiv-cs.CL | 2022-12-06 |
| 2 | Neural Machine Translation with Contrastive Translation Memories Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Different from previous works that make use of mutually similar but redundant translation memories~(TMs), we propose a new retrieval-augmented NMT to model contrastively retrieved translation memories that are holistically similar to the source sentence while individually contrastive to each other providing maximal information gains in three phases. |
Xin Cheng; Shen Gao; Lemao Liu; Dongyan Zhao; Rui Yan; | arxiv-cs.CL | 2022-12-06 |
| 3 | Impact of Domain-Adapted Multilingual Neural Machine Translation in The Medical Domain Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We compare the out-of-domain MNMT with the in-domain adapted MNMT. |
Miguel Rios; Raluca-Maria Chereji; Alina Secara; Dragos Ciobanu; | arxiv-cs.CL | 2022-12-05 |
| 4 | In-context Examples Selection for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to understand the properties of good in-context examples for MT in both in-domain and out-of-domain settings. |
Sweta Agrawal; Chunting Zhou; Mike Lewis; Luke Zettlemoyer; Marjan Ghazvininejad; | arxiv-cs.CL | 2022-12-05 |
| 5 | Democratizing Machine Translation with OPUS-MT Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the OPUS ecosystem with a focus on the development of open machine translation models and tools, and their integration into end-user applications, development platforms and professional workflows. |
JÖRG TIEDEMANN et. al. | arxiv-cs.CL | 2022-12-04 |
| 6 | The RoyalFlush System for The WMT 2022 Efficiency Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. |
BO QIN et. al. | arxiv-cs.CL | 2022-12-03 |
| 7 | Tackling Low-Resourced Sign Language Translation: UPC at WMT-SLT 22 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes the system developed at the Universitat Polit\`ecnica de Catalunya for the Workshop on Machine Translation 2022 Sign Language Translation Task, in particular, for the sign-to-text direction. |
Laia Tarrés; Gerard I. Gàllego; Xavier Giró-i-Nieto; Jordi Torres; | arxiv-cs.CL | 2022-12-02 |
| 8 | CUNI Systems for The WMT22 Czech-Ukrainian Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Charles University submissions to the WMT22 General Translation Shared Task on Czech-Ukrainian and Ukrainian-Czech machine translation. |
Martin Popel; Jindřich Libovický; Jindřich Helcl; | arxiv-cs.CL | 2022-12-01 |
| 9 | Word Alignment in The Era of Deep Learning: A Tutorial Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The word alignment task, despite its prominence in the era of statistical machine translation (SMT), is niche and under-explored today. In this two-part tutorial, we argue for the continued relevance for word alignment. |
Bryan Li; | arxiv-cs.CL | 2022-11-30 |
| 10 | VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech. |
YIHAN WU et. al. | arxiv-cs.CL | 2022-11-30 |
| 11 | Extending The Subwording Model of Multilingual Pretrained Models for New Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we add new subwords to the SentencePiece tokenizer to apply a multilingual pretrained model to new languages (Inuktitut in this paper). |
Kenji Imamura; Eiichiro Sumita; | arxiv-cs.CL | 2022-11-29 |
| 12 | CUNI Submission in WMT22 General Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the CUNI-Bergamot submission for the WMT22 General translation task. |
Josef Jon; Martin Popel; Ondřej Bojar; | arxiv-cs.CL | 2022-11-29 |
| 13 | Findings of The WMT 2022 Shared Task on Translation Suggestion Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We report the result of the first edition of the WMT shared task on Translation Suggestion (TS). |
Zhen Yang; Fandong Meng; Yingxue Zhang; Ernan Li; Jie Zhou; | arxiv-cs.CL | 2022-11-29 |
| 14 | Domain Mismatch Doesn’t Always Prevent Cross-Lingual Transfer Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that a simple initialization regimen can overcome much of the effect of domain mismatch in cross-lingual transfer. |
Daniel Edmiston; Phillip Keung; Noah A. Smith; | arxiv-cs.CL | 2022-11-29 |
| 15 | Considerations for Meaningful Sign Language Machine Translation Based on Glosses Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we review recent works on neural gloss translation. |
Mathias Müller; Zifan Jiang; Amit Moryossef; Annette Rios; Sarah Ebling; | arxiv-cs.CL | 2022-11-28 |
| 16 | Summer: WeChat Neural Machine Translation Systems for The WMT22 Biomedical Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces WeChat’s participation in WMT 2022 shared biomedical translation task on Chinese to English. |
Ernan Li; Fandong Meng; Jie Zhou; | arxiv-cs.CL | 2022-11-27 |
| 17 | BJTU-WeChat’s Systems for The WMT22 Chat Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces the joint submission of the Beijing Jiaotong University and WeChat AI to the WMT’22 chat translation task for English-German. |
Yunlong Liang; Fandong Meng; Jinan Xu; Yufeng Chen; Jie Zhou; | arxiv-cs.CL | 2022-11-27 |
| 18 | Competency-Aware Neural Machine Translation: Can Machine Translation Know Its Own Translation Quality? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This is in sharp contrast to human translators who give feedback or conduct further investigations whenever they are in doubt about predictions. To fill this gap, we propose a novel competency-aware NMT by extending conventional NMT with a self-estimator, offering abilities to translate a source sentence and estimate its competency. |
PEI ZHANG et. al. | arxiv-cs.CL | 2022-11-24 |
| 19 | Breaking The Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a novel representation method for Chinese characters to break the bottlenecks, namely StrokeNet, which represents a Chinese character by a Latinized stroke sequence (e.g., ao1 (concave) to ajaie and tu1 (convex) to aeaqe). |
Zhijun Wang; Xuebo Liu; Min Zhang; | arxiv-cs.CL | 2022-11-23 |
| 20 | ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic – English Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we collect translations in both directions, monolingual Egyptian Arabic and monolingual English, forming a three-way speech translation corpus. |
Injy Hamed; Nizar Habash; Slim Abdennadher; Ngoc Thang Vu; | arxiv-cs.CL | 2022-11-21 |
| 21 | A Copy Mechanism for Handling Knowledge Base Elements in SPARQL Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, current architectures are unable to integrate the knowledge base (KB) schema and handle questions on knowledge resources, classes, and properties unseen during training, rendering them unusable outside the scope of topics covered in the training set. Inspired by the performance gains in natural language processing tasks, we propose to integrate a copy mechanism for neural SPARQL query generation as a way to tackle this issue. |
Rose Hirigoyen; Amal Zouaq; Samuel Reyd; | arxiv-cs.CL | 2022-11-18 |
| 22 | Back-Translation-Style Data Augmentation for Mandarin Chinese Polyphone Disambiguation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose a simple back-translation-style data augmentation method for mandarin Chinese polyphone disambiguation, utilizing a large amount of unlabeled text data. |
CHUNYU QIANG et. al. | arxiv-cs.SD | 2022-11-17 |
| 23 | Prompting PaLM for Translation: Assessing Strategies and Performance Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate various strategies for choosing translation examples for few-shot prompting, concluding that example quality is the most important factor. |
DAVID VILAR et. al. | arxiv-cs.CL | 2022-11-16 |
| 24 | TSMind: Alibaba and Soochow University’s Submission to The WMT22 Translation Suggestion Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes the joint submission of Alibaba and Soochow University, TSMind, to the WMT 2022 Shared Task on Translation Suggestion (TS). |
XIN GE et. al. | arxiv-cs.CL | 2022-11-16 |
| 25 | MT Metrics Correlate with Human Ratings of Simultaneous Speech Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: It is unclear whether human ratings of simultaneous speech translation Continuous Rating (CR) correlate with these metrics or not. Therefore, we conduct an extensive correlation analysis of CR and the aforementioned automatic metrics on evaluations of candidate systems at English-German simultaneous speech translation task at IWSLT 2022. |
Dominik Macháček; Ondřej Bojar; Raj Dabre; | arxiv-cs.CL | 2022-11-15 |
| 26 | Findings of The Covid-19 MLIA Machine Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents the results of the machine translation (MT) task from the Covid-19 MLIA @ Eval initiative, a community effort to improve the generation of MT systems focused on the current Covid-19 crisis. |
FRANCISCO CASACUBERTA et. al. | arxiv-cs.CL | 2022-11-14 |
| 27 | Easy Guided Decoding in Providing Suggestions for Interactive Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we utilize the parameterized objective function of neural machine translation and propose an easy constrained decoding algorithm to improve the translation quality without additional training. |
Ke Wang; Xin Ge; Yuqi Zhang; Yu Zhao; Jiayi Wang; | arxiv-cs.CL | 2022-11-13 |
| 28 | Grammatical Error Correction: A Survey of The State of The Art Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this survey paper, we condense the field into a single article and first outline some of the linguistic challenges of the task, introduce the most popular datasets that are available to researchers (for both English and other languages), and summarise the various methods and techniques that have been developed with a particular focus on artificial error generation. |
CHRISTOPHER BRYANT et. al. | arxiv-cs.CL | 2022-11-09 |
| 29 | ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose ERNIE-UniX2, a unified cross-lingual cross-modal pre-training framework for both generation and understanding tasks. |
BIN SHAN et. al. | arxiv-cs.CV | 2022-11-09 |
| 30 | Review of Coreference Resolution in English and Persian Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Consequently, it has a significant effect on the quality of these systems. This article reviews the existing corpora and evaluation metrics in this field. |
Hassan Haji Mohammadi; Alireza Talebpour; Ahmad Mahmoudi Aznaveh; Samaneh Yazdani; | arxiv-cs.CL | 2022-11-08 |
| 31 | InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose InsNet, an expressive insertion-based text generator with efficient training and flexible decoding (parallel or sequential). |
Sidi Lu; Tao Meng; Nanyun Peng; | nips | 2022-11-06 |
| 32 | Refining Low-Resource Unsupervised Translation By Language Disentanglement of Multilingual Translation Model Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a simple refinement procedure to separate languages from a pre-trained multilingual UMT model for it to focus on only the target low-resource task. |
Xuan-Phi Nguyen; Shafiq Joty; Kui Wu; Ai Ti Aw; | nips | 2022-11-06 |
| 33 | MT-GenEval: A Counterfactual and Contextual Dataset for Evaluating Gender Accuracy in Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce MT-GenEval, a benchmark for evaluating gender accuracy in translation from English into eight widely-spoken languages. |
ANNA CURREY et. al. | arxiv-cs.CL | 2022-11-02 |
| 34 | Domain Curricula for Code-Switched MT at MixMT 2022 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present our approach and results for the Code-mixed Machine Translation (MixMT) shared task at WMT 2022: the task consists of two subtasks, monolingual to code-mixed machine translation (Subtask-1) and code-mixed to monolingual machine translation (Subtask-2). |
Lekan Raheem; Maab Elrashid; | arxiv-cs.CL | 2022-10-31 |
| 35 | Domain Adaptation of Machine Translation with Crowdworkers Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a framework that efficiently and effectively collects parallel sentences in a target domain from the web with the help of crowdworkers. |
Makoto Morishita; Jun Suzuki; Masaaki Nagata; | arxiv-cs.CL | 2022-10-27 |
| 36 | ACES: Translation Accuracy Challenge Sets for Evaluating Machine Translation Metrics Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We use ACES to evaluate a wide range of MT metrics including the submissions to the WMT 2022 metrics shared task and perform several analyses leading to general recommendations for metric developers. |
Chantal Amrhein; Nikita Moghe; Liane Guillou; | arxiv-cs.CL | 2022-10-27 |
| 37 | COMET-QE and Active Learning for Low-Resource Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We use COMET-QE, a reference-free evaluation metric, to select sentences for low-resource neural machine translation. |
Everlyn Asiko Chimoto; Bruce A. Bassett; | arxiv-cs.CL | 2022-10-27 |
| 38 | The Effect of Normalization for Bi-directional Amharic-English Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper presents the first relatively large-scale Amharic-English parallel sentence dataset. |
TADESSE DESTAW BELAY et. al. | arxiv-cs.CL | 2022-10-27 |
| 39 | Improving Speech-to-Speech Translation Through Unlabeled Text Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an effective way to utilize the massive existing unlabeled text from different languages to create a large amount of S2ST data to improve S2ST performance by applying various acoustic effects to the generated synthetic data. |
XUAN-PHI NGUYEN et. al. | arxiv-cs.CL | 2022-10-26 |
| 40 | A Bilingual Parallel Corpus with Discourse Annotations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes BWB, a large parallel corpus first introduced in Jiang et al. (2022), along with an annotated test set. |
YUCHEN ELEANOR JIANG et. al. | arxiv-cs.CL | 2022-10-26 |
| 41 | Smart Speech Segmentation Using Acousto-Linguistic Features with Look-ahead Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a hybrid approach that leverages both acoustic and language information to improve segmentation. |
PIYUSH BEHRE et. al. | arxiv-cs.CL | 2022-10-25 |
| 42 | Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: The experts note that MT outputs contain not only mistranslations, but also discourse-disrupting errors and stylistic inconsistencies. To address these problems, we train a post-editing model whose output is preferred over normal MT output at a rate of 69% by experts. |
KATHERINE THAI et. al. | arxiv-cs.CL | 2022-10-25 |
| 43 | DEMETR: Diagnosing Evaluation Metrics for Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: The operations of newer learned metrics (e.g., BLEURT, COMET), which leverage pretrained language models to achieve higher correlations with human quality judgments than BLEU, are opaque in comparison. In this paper, we shed light on the behavior of these learned metrics by creating DEMETR, a diagnostic dataset with 31K English examples (translated from 10 source languages) for evaluating the sensitivity of MT evaluation metrics to 35 different linguistic perturbations spanning semantic, syntactic, and morphological error categories. |
MARZENA KARPINSKA et. al. | arxiv-cs.CL | 2022-10-24 |
| 44 | Bilingual Synchronization: Restoring Translational Relationships with Editing Operations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider here a more general setting which assumes an initial target sequence, that must be transformed into a valid translation of the source, thereby restoring parallelism between source and target. |
Jitao Xu; Josep Crego; François Yvon; | arxiv-cs.CL | 2022-10-24 |
| 45 | Focused Concatenation for Context-Aware Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose an improved concatenation approach that encourages the model to focus on the translation of the current sentence, discounting the loss generated by target context. |
Lorenzo Lupo; Marco Dinarelli; Laurent Besacier; | arxiv-cs.CL | 2022-10-24 |
| 46 | Analyzing The Use of Influence Functions for Instance-Specific Data Filtering in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we examine the use of influence functions for Neural Machine Translation (NMT). |
Tsz Kin Lam; Eva Hasler; Felix Hieber; | arxiv-cs.CL | 2022-10-24 |
| 47 | Translation Word-Level Auto-Completion: What Can We Achieve Out of The Box? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work describes our submissions to WMT’s shared task on word-level auto-completion, for the Chinese-to-English, English-to-Chinese, German-to-English, and English-to-German language directions. |
Yasmin Moslem; Rejwanul Haque; Andy Way; | arxiv-cs.CL | 2022-10-23 |
| 48 | Additive Interventions Yield Robust Multi-Domain Machine Translation Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast to tag-based approaches which manipulate the raw source sequence, interventions work by directly modulating the encoder representation of all tokens in the sequence. We examine the role of additive interventions in a large-scale multi-domain machine translation setting and compare its performance in various inference scenarios. |
Elijah Rippeth; Matt Post; | arxiv-cs.CL | 2022-10-23 |
| 49 | Information-Transport-based Policy for Simultaneous Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we treat the translation as information transport from source to target and accordingly propose an Information-Transport-based Simultaneous Translation (ITST). |
Shaolei Zhang; Yang Feng; | arxiv-cs.CL | 2022-10-22 |
| 50 | A Semi-supervised Approach for A Better Translation of Sentiment in Dialectical Arabic UGT Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this research, we aim to improve the translation of sentiment in UGT written in the dialectical versions of the Arabic language to English. |
Hadeel Saadany; Constantin Orasan; Emad Mohamed; Ashraf Tantawy; | arxiv-cs.CL | 2022-10-21 |
| 51 | Turning Fixed to Adaptive: Integrating Post-Evaluation Into Simultaneous Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a method of performing the adaptive policy via integrating post-evaluation into the fixed policy. |
Shoutao Guo; Shaolei Zhang; Yang Feng; | arxiv-cs.CL | 2022-10-21 |
| 52 | Gui at MixMT 2022 : English-Hinglish: An MT Approach for Translation of Code Mixed Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we discuss the use of mBART with some special pre-processing and post-processing (transliteration from Devanagari to Roman) for the first task in detail and the experiments that we performed for the second task of translating code-mixed Hinglish to monolingual English. |
AKSHAT GAHOI et. al. | arxiv-cs.CL | 2022-10-21 |
| 53 | Is Encoder-Decoder Redundant for Neural Machine Translation? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the aforementioned concept for machine translation. |
Yingbo Gao; Christian Herold; Zijian Yang; Hermann Ney; | arxiv-cs.CL | 2022-10-21 |
| 54 | University of Cape Town’s WMT22 System: Multilingual Machine Translation for Southern African Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The paper describes the University of Cape Town’s submission to the constrained track of the WMT22 Shared Task: Large-Scale Machine Translation Evaluation for African Languages. |
Khalid N. Elmadani; Francois Meyer; Jan Buys; | arxiv-cs.CL | 2022-10-21 |
| 55 | The University of Edinburgh’s Submission to The WMT22 Code-Mixing Shared Task (MixMT) Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: For subtask 2, we investigated different pretraining techniques, namely comparing simple initialisation from existing machine translation models and aligned augmentation. |
Faheem Kirefu; Vivek Iyer; Pinzhen Chen; Laurie Burchell; | arxiv-cs.CL | 2022-10-20 |
| 56 | Multi-Granularity Optimization for Non-Autoregressive Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This assumption is further strengthened by cross-entropy loss, which encourages a strict match between the hypothesis and the reference token by token. To alleviate this issue, we propose multi-granularity optimization for NAT, which collects model behaviors on translation segments of various granularities and integrates feedback for backpropagation. |
Yafu Li; Leyang Cui; Yongjing Yin; Yue Zhang; | arxiv-cs.CL | 2022-10-20 |
| 57 | Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a Wait-info Policy to balance source and target at the information level. |
Shaolei Zhang; Shoutao Guo; Yang Feng; | arxiv-cs.CL | 2022-10-20 |
| 58 | Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Previous works mostly focus on either multilingual or multi-domain aspects of neural machine translation (NMT). |
Thuy-Trang Vu; Shahram Khadivi; Xuanli He; Dinh Phung; Gholamreza Haffari; | arxiv-cs.CL | 2022-10-20 |
| 59 | SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes the Stevens Institute of Technology’s submission for the WMT 2022 Shared Task: Code-mixed Machine Translation (MixMT). |
Abdul Rafae Khan; Hrishikesh Kanade; Girish Amar Budhrani; Preet Jhanglani; Jia Xu; | arxiv-cs.CL | 2022-10-20 |
| 60 | The VolcTrans System for WMT22 Multilingual Machine Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This report describes our VolcTrans system for the WMT22 shared task on large-scale multilingual machine translation. |
XIAN QIAN et. al. | arxiv-cs.CL | 2022-10-20 |
| 61 | Separating Grains from The Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work describes our approach, which is based on filtering the given noisy data using a sentence-pair classifier that was built by fine-tuning a pre-trained language model. |
IDRIS ABDULMUMIN et. al. | arxiv-cs.CL | 2022-10-19 |
| 62 | LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recent advances still struggle to train a separate model for each language pair, which is costly and unaffordable when the number of languages increases in the real world. |
HONGCHENG GUO et. al. | arxiv-cs.CL | 2022-10-19 |
| 63 | TM2T: Stochastic and Tokenized Modeling for The Reciprocal Generation of 3D Human Motions and Texts Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Inspired by the strong ties between vision and language, the two intimate human sensing and communication modalities, our paper aims to explore the generation of 3D human full-body motions from texts, as well as its reciprocal task, shorthanded for text2motion and motion2text, respectively. |
Chuan Guo; Xinxin Zuo; Sen Wang; Li Cheng; | eccv | 2022-10-19 |
| 64 | Hybrid-Regressive Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we empirically confirm that non-autoregressive translation with an iterative refinement mechanism (IR-NAT) suffers from poor acceleration robustness because it is more sensitive to decoding batch size and computing device setting than autoregressive translation (AT). |
Qiang Wang; Xinhui Hu; Ming Chen; | arxiv-cs.CL | 2022-10-19 |
| 65 | Domain Specific Sub-network for Multi-Domain Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents Domain-Specific Sub-network (DoSS). |
Amr Hendy; Mohamed Abdelghaffar; Mohamed Afify; Ahmed Y. Tawfik; | arxiv-cs.CL | 2022-10-18 |
| 66 | Simple and Effective Unsupervised Speech Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details 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. | arxiv-cs.CL | 2022-10-18 |
| 67 | Tencent’s Multilingual Machine Translation System for WMT22 Large-Scale African Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper describes Tencent’s multilingual machine translation systems for the WMT22 shared task on Large-Scale Machine Translation Evaluation for African Languages. |
WENXIANG JIAO et. al. | arxiv-cs.CL | 2022-10-18 |
| 68 | Tencent AI Lab – Shanghai Jiao Tong University Low-Resource Translation System for The WMT22 Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper describes Tencent AI Lab – Shanghai Jiao Tong University (TAL-SJTU) Low-Resource Translation systems for the WMT22 shared task. |
Zhiwei He; Xing Wang; Zhaopeng Tu; Shuming Shi; Rui Wang; | arxiv-cs.CL | 2022-10-17 |
| 69 | Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In order to enable zero-shot ST, we propose a novel Discrete Cross-Modal Alignment (DCMA) method that employs a shared discrete vocabulary space to accommodate and match both modalities of speech and text. |
CHEN WANG et. al. | arxiv-cs.CL | 2022-10-17 |
| 70 | Modeling Context With Linear Attention for Scalable Document-Level Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the efficacy of a recent linear attention model by Peng et al. (2021) on document translation and augment it with a sentential gate to promote a recency inductive bias. |
Zhaofeng Wu; Hao Peng; Nikolaos Pappas; Noah A. Smith; | arxiv-cs.CL | 2022-10-15 |
| 71 | Low-resource Neural Machine Translation with Cross-modal Alignment Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we turn to connect several low-resource languages to a particular high-resource one by additional visual modality. |
Zhe Yang; Qingkai Fang; Yang Feng; | arxiv-cs.CL | 2022-10-13 |
| 72 | Categorizing Semantic Representations for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, they have recently been shown to suffer limitation in compositional generalization, failing to effectively learn the translation of atoms (e.g., words) and their semantic composition (e.g., modification) from seen compounds (e.g., phrases), and thus suffering from significantly weakened translation performance on unseen compounds during inference. We address this issue by introducing categorization to the source contextualized representations. |
Yongjing Yin; Yafu Li; Fandong Meng; Jie Zhou; Yue Zhang; | arxiv-cs.CL | 2022-10-13 |
| 73 | DATScore: Evaluating Translation with Data Augmented Translations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the recent work of BARTScore: a metric leveraging the BART language model to evaluate the quality of generated text from various aspects, we introduce DATScore. |
Moussa Kamal Eddine; Guokan Shang; Michalis Vazirgiannis; | arxiv-cs.CL | 2022-10-12 |
| 74 | Improved Data Augmentation for Translation Suggestion Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces the system used in our submission to the WMT’22 Translation Suggestion shared task. |
HONGXIAO ZHANG et. al. | arxiv-cs.CL | 2022-10-12 |
| 75 | Non-Autoregressive Machine Translation with Translation Memories Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: By modifying the data presentation and introducing an extra deletion operation, we obtain performance that are on par with an autoregressive approach, while reducing the decoding load. |
Jitao Xu; Josep Crego; François Yvon; | arxiv-cs.CL | 2022-10-12 |
| 76 | Using Massive Multilingual Pre-Trained Language Models Towards Real Zero-Shot Neural Machine Translation in Clinical Domain Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate whether MMPLMs can be applied to zero-shot machine translation (MT) toward entirely new language pairs and new domains. |
Lifeng Han; Gleb Erofeev; Irina Sorokina; Serge Gladkoff; Goran Nenadic; | arxiv-cs.CL | 2022-10-12 |
| 77 | CTC Alignments Improve Autoregressive Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we argue that CTC does in fact make sense for translation if applied in a joint CTC/attention framework wherein CTC’s core properties can counteract several key weaknesses of pure-attention models during training and decoding. |
BRIAN YAN et. al. | arxiv-cs.CL | 2022-10-11 |
| 78 | Streaming Punctuation for Long-form Dictation with Transformers Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Automatic Speech Recognition (ASR) production systems, however, are constrained by real-time requirements, making it hard to incorporate the right context when making punctuation decisions. In this paper, we propose a streaming approach for punctuation or re-punctuation of ASR output using dynamic decoding windows and measure its impact on punctuation and segmentation accuracy across scenarios. |
Piyush Behre; Sharman Tan; Padma Varadharajan; Shuangyu Chang; | arxiv-cs.CL | 2022-10-11 |
| 79 | Machine Translation Between Spoken Languages and Signed Languages Represented in SignWriting Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper presents work on novel machine translation (MT) systems between spoken and signed languages, where signed languages are represented in SignWriting, a sign language writing system. |
Zifan Jiang; Amit Moryossef; Mathias Müller; Sarah Ebling; | arxiv-cs.CL | 2022-10-11 |
| 80 | Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we present a Viterbi decoding framework for DA-Transformer, which guarantees to find the joint optimal solution for the translation and decoding path under any length constraint. |
Chenze Shao; Zhengrui Ma; Yang Feng; | arxiv-cs.CL | 2022-10-11 |
| 81 | Distill The Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Thus, in this work, we introduce IKD-MMT, a novel MMT framework to support the image-free inference phase via an inversion knowledge distillation scheme. |
Ru Peng; Yawen Zeng; Junbo Zhao; | arxiv-cs.CL | 2022-10-10 |
| 82 | Improving Robustness of Retrieval Augmented Translation Via Shuffling of Suggestions Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a simple method to expose fuzzy-match NMT systems during training and show that it results in a system that is much more tolerant (regaining up to 5.8 BLEU) to inference with TMs with domain mismatch. |
Cuong Hoang; Devendra Sachan; Prashant Mathur; Brian Thompson; Marcello Federico; | arxiv-cs.CL | 2022-10-10 |
| 83 | Checks and Strategies for Enabling Code-Switched Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work explores multilingual NMT models’ ability to handle code-switched text. |
Thamme Gowda; Mozhdeh Gheini; Jonathan May; | arxiv-cs.CL | 2022-10-10 |
| 84 | Automatic Evaluation and Analysis of Idioms in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, first, we propose a novel metric for automatically measuring the frequency of literal translation errors without human involvement. Equipped with this metric, we present controlled translation experiments with models trained in different conditions (with/without the test-set idioms) and across a wide range of (global and targeted) metrics and test sets. |
Christos Baziotis; Prashant Mathur; Eva Hasler; | arxiv-cs.CL | 2022-10-10 |
| 85 | Ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Starting from the intuition that reordering generally occurs between phrases, we extend oaxe by only allowing reordering between ngram phrases and still requiring a strict match of word order within the phrases. |
Cunxiao Du; Zhaopeng Tu; Longyue Wang; Jing Jiang; | arxiv-cs.CL | 2022-10-08 |
| 86 | Improving End-to-End Text Image Translation From The Auxiliary Text Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a novel text translation enhanced text image translation, which trains the end-to-end model with text translation as an auxiliary task. |
CONG MA et. al. | arxiv-cs.CL | 2022-10-07 |
| 87 | Toxicity in Multilingual Machine Translation at Scale Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we focus on one type of critical error: added toxicity. |
MARTA R. COSTA-JUSSÀ et. al. | arxiv-cs.CL | 2022-10-06 |
| 88 | The Boundaries of Meaning: A Case Study in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: But do they have any linguistic or philosophical plausibility? I attempt to cast light on this question by reviewing the relevant details of the subword segmentation algorithms and by relating them to important philosophical and linguistic debates, in the spirit of making artificial intelligence more transparent and explainable. |
Yuri Balashov; | arxiv-cs.CL | 2022-10-02 |
| 89 | MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We empirically demonstrate the effectiveness of self-supervised pre-training and data augmentation for zero-shot multi-lingual machine translation. |
Kshitij Gupta; | arxiv-cs.CL | 2022-10-01 |
| 90 | FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present FRMT, a new dataset and evaluation benchmark for Few-shot Region-aware Machine Translation, a type of style-targeted translation. |
PARKER RILEY et. al. | arxiv-cs.CL | 2022-10-01 |
| 91 | On The Robustness of Self-Supervised Representations for Spoken Language Modeling Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: First, we empirically demonstrate how current state-of-the-art speech representation models lack robustness to basic signal variations that do not alter the spoken information. To overcome this, we propose an effective and efficient method to learn robust self-supervised speech representation for generative spoken language modeling. |
ITAI GAT et. al. | arxiv-cs.CL | 2022-09-30 |
| 92 | QUAK: A Synthetic Quality Estimation Dataset for Korean-English Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Despite its high utility in the real world, there remain several limitations concerning manual QE data creation: inevitably incurred non-trivial costs due to the need for translation experts, and issues with data scaling and language expansion. To tackle these limitations, we present QUAK, a Korean-English synthetic QE dataset generated in a fully automatic manner. |
SUGYEONG EO et. al. | arxiv-cs.CL | 2022-09-30 |
| 93 | Blur The Linguistic Boundary: Interpreting Chinese Buddhist Sutra in English Via Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we proposed a novel approach to building a practical NMT model for Buddhist scriptures. |
DENGHAO LI et. al. | arxiv-cs.CL | 2022-09-29 |
| 94 | Effective General-Domain Data Inclusion for The Machine Translation Task By Vanilla Transformers Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Not only it is revolutionary for various translation tasks, but also for a majority of other NLP tasks. In this paper, we aim at a Transformer-based system that is able to translate a source sentence in German to its counterpart target sentence in English. |
Hassan Soliman; | arxiv-cs.CL | 2022-09-28 |
| 95 | An Automatic Evaluation of The WMT22 General Machine Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This report presents an automatic evaluation of the general machine translation task of the Seventh Conference on Machine Translation (WMT22). |
Benjamin Marie; | arxiv-cs.CL | 2022-09-28 |
| 96 | Improving Multilingual Neural Machine Translation System for Indic Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a MNMT system to address the issues related to low-resource language translation. |
Sudhansu Bala Das; Atharv Biradar; Tapas Kumar Mishra; Bidyut Kumar Patra; | arxiv-cs.CL | 2022-09-27 |
| 97 | Meta-Learning A Cross-lingual Manifold for Semantic Parsing Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a first-order meta-learning algorithm to train a semantic parser with maximal sample efficiency during cross-lingual transfer. |
Tom Sherborne; Mirella Lapata; | arxiv-cs.CL | 2022-09-26 |
| 98 | A Deep Investigation of RNN and Self-attention for The Cyrillic-Traditional Mongolian Bidirectional Conversion Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, an open problem remains as to whether the CTMBC quality can be improved by utilizing the RNN and Transformer models. To answer this question, this paper investigates the utility of these two powerful techniques for CTMBC task combined with agglutinative characteristics of Mongolian language. |
Muhan Na; Rui Liu; Feilong; Guanglai Gao; | arxiv-cs.CL | 2022-09-24 |
| 99 | Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a non-tuning paradigm, resolving domain adaptation with a prompt-based method. |
ZEWEI SUN et. al. | arxiv-cs.CL | 2022-09-23 |
| 100 | Approaching English-Polish Machine Translation Quality Assessment with Neural-based Methods Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents our contribution to the PolEval 2021 Task 2: Evaluation of translation quality assessment metrics. |
Artur Nowakowski; | arxiv-cs.CL | 2022-09-22 |
| 101 | PePe: Personalized Post-editing Model Utilizing User-generated Post-edits Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Despite the recent advancement of machine translation, it remains a demanding task to properly reflect personal style. In this paper, we introduce a personalized automatic post-editing framework to address this challenge, which effectively generates sentences considering distinct personal behaviors. |
Jihyeon Lee; Taehee Kim; Yunwon Tae; Cheonbok Park; Jaegul Choo; | arxiv-cs.CL | 2022-09-21 |
| 102 | Vega-MT: The JD Explore Academy Translation System for WMT22 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe the JD Explore Academy’s submission of the WMT 2022 shared general translation task. |
CHANGTONG ZAN et. al. | arxiv-cs.CL | 2022-09-19 |
| 103 | A Snapshot Into The Possibility of Video Game Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present in this article what we believe to be one of the first attempts at video game machine translation. |
Damien Hansen; Pierre-Yves Houlmont; | arxiv-cs.CL | 2022-09-19 |
| 104 | The First Neural Machine Translation System for The Erzya Language Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present the first neural machine translation system for translation between the endangered Erzya language and Russian and the dataset collected by us to train and evaluate it. |
David Dale; | arxiv-cs.CL | 2022-09-19 |
| 105 | Learning Decoupled Retrieval Representation for Nearest Neighbour Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Generally, kNN-MT borrows the off-the-shelf context representation in the translation task, e.g., the output of the last decoder layer, as the query vector of the retrieval task. In this work, we highlight that coupling the representations of these two tasks is sub-optimal for fine-grained retrieval. |
Qiang Wang; Rongxiang Weng; Ming Chen; | arxiv-cs.CL | 2022-09-18 |
| 106 | Rethinking Round-trip Translation for Automatic Machine Translation Evaluation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We conduct extensive experiments to show the effectiveness and robustness of the predictive models on 1,000+ language pairs. |
Terry Yue Zhuo; Qiongkai Xu; Xuanli He; Trevor Cohn; | arxiv-cs.CL | 2022-09-15 |
| 107 | Data-adaptive Transfer Learning for Translation: A Case Study in Haitian and Jamaican Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Multilingual transfer techniques often improve low-resource machine translation (MT). |
Nathaniel R. Robinson; Cameron J. Hogan; Nancy Fulda; David R. Mortensen; | arxiv-cs.CL | 2022-09-13 |
| 108 | Rethink About The Word-level Quality Estimation for Machine Translation from Human Judgement Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Typically, conventional works on word-level QE are designed to predict the translation quality in terms of the post-editing effort, where the word labels (OK and BAD) are automatically generated by comparing words between MT sentences and the post-edited sentences through a Translation Error Rate (TER) toolkit. |
Zhen Yang; Fandong Meng; Yuanmeng Yan; Jie Zhou; | arxiv-cs.CL | 2022-09-12 |
| 109 | Adapting to Non-Centered Languages for Zero-shot Multilingual Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose a simple, lightweight yet effective language-specific modeling method by adapting to non-centered languages and combining the shared information and the language-specific information to counteract the instability of zero-shot translation. |
Zhi Qu; Taro Watanabe; | arxiv-cs.CL | 2022-09-09 |
| 110 | Adam Mickiewicz University at WMT 2022: NER-Assisted and Quality-Aware Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents Adam Mickiewicz University’s (AMU) submissions to the constrained track of the WMT 2022 General MT Task. |
Artur Nowakowski; Gabriela Pałka; Kamil Guttmann; Mikołaj Pokrywka; | arxiv-cs.CL | 2022-09-07 |
| 111 | On The Complementarity Between Pre-Training and Random-Initialization for Resource-Rich Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We take the first step to investigate the complementarity between PT and RI in resource-rich scenarios via two probing analyses, and find that: 1) PT improves NOT the accuracy, but the generalization by achieving flatter loss landscapes than that of RI; 2) PT improves NOT the confidence of lexical choice, but the negative diversity by assigning smoother lexical probability distributions than that of RI. Based on these insights, we propose to combine their complementarities with a model fusion algorithm that utilizes optimal transport to align neurons between PT and RI. |
CHANGTONG ZAN et. al. | arxiv-cs.CL | 2022-09-07 |
| 112 | Facilitating Global Team Meetings Between Language-Based Subgroups: When and How Can Machine Translation Help? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the current study, we investigate the idea of leveraging machine translation (MT) to facilitate global team meetings. |
Yongle Zhang; Dennis Asamoah Owusu; Marine Carpuat; Ge Gao; | arxiv-cs.CL | 2022-09-06 |
| 113 | Rare But Severe Neural Machine Translation Errors Induced By Minimal Deletion: An Empirical Study on Chinese and English Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We examine the inducement of rare but severe errors in English-Chinese and Chinese-English in-domain neural machine translation by minimal deletion of the source text with character-based models. |
Ruikang Shi; Alvin Grissom II; Duc Minh Trinh; | arxiv-cs.CL | 2022-09-05 |
| 114 | Informative Language Representation Learning for Massively Multilingual Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: However, recent studies show that prepending language tokens sometimes fails to navigate the multilingual neural machine translation models into right translation directions, especially on zero-shot translation. To mitigate this issue, we propose two methods, language embedding embodiment and language-aware multi-head attention, to learn informative language representations to channel translation into right directions. |
Renren Jin; Deyi Xiong; | arxiv-cs.CL | 2022-09-04 |
| 115 | Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a noise-robust cross-lingual cross-modal retrieval method for low-resource languages. |
YABING WANG et. al. | arxiv-cs.CV | 2022-08-26 |
| 116 | Nearest Neighbor Non-autoregressive Text Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Previous studies addressed this issue through iterative decoding. This study proposes using nearest neighbors as the initial state of an NAR decoder and editing them iteratively. |
Ayana Niwa; Sho Takase; Naoaki Okazaki; | arxiv-cs.CL | 2022-08-26 |
| 117 | Kencorpus: A Kenyan Language Corpus of Swahili, Dholuo and Luhya for Natural Language Processing Tasks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Kencorpus is a Kenyan Language corpus that intends to bridge the gap on how to collect, and store text and speech data that is good enough to enable data-driven solutions in applications such as machine translation, question answering and transcription in multilingual communities. |
BARACK WANJAWA et. al. | arxiv-cs.CL | 2022-08-25 |
| 118 | Improving Video Retrieval Using Multilingual Knowledge Transfer Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a framework MKTVR, that utilizes knowledge transfer from a multilingual model to boost the performance of video retrieval. |
AVINASH MADASU et. al. | arxiv-cs.CV | 2022-08-24 |
| 119 | Domain-Specific Text Generation for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose a novel approach to domain adaptation leveraging state-of-the-art pretrained language models (LMs) for domain-specific data augmentation for MT, simulating the domain characteristics of either (a) a small bilingual dataset, or (b) the monolingual source text to be translated. |
Yasmin Moslem; Rejwanul Haque; John D. Kelleher; Andy Way; | arxiv-cs.CL | 2022-08-11 |
| 120 | Looking for A Needle in A Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we set foundations for the study of NMT hallucinations. |
Nuno M. Guerreiro; Elena Voita; André F. T. Martins; | arxiv-cs.CL | 2022-08-10 |
| 121 | Mismatching-Aware Unsupervised Translation Quality Estimation For Low-Resource Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We evaluate the proposed method on four low-resource language pairs of WMT21 QE shared task, as well as a new English-Farsi test dataset introduced in this paper. |
Fatemeh Azadi; Heshaam Faili; Mohammad Javad Dousti; | arxiv-cs.CL | 2022-07-31 |
| 122 | Thutmose Tagger: Single-pass Neural Model for Inverse Text Normalization Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Unfortunately, such neural models are prone to hallucinations that could lead to unacceptable errors. To mitigate this issue, we propose a single-pass token classifier model that regards ITN as a tagging task. |
Alexandra Antonova; Evelina Bakhturina; Boris Ginsburg; | arxiv-cs.CL | 2022-07-29 |
| 123 | Benchmarking Azerbaijani Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we benchmark the performance of Azerbaijani-English NMT systems on a range of techniques and datasets. |
Chih-Chen Chen; William Chen; | arxiv-cs.CL | 2022-07-29 |
| 124 | GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: However, vanilla Transformer mainly exploits the top-layer representation, assuming the lower layers provide trivial or redundant information and thus ignoring the bottom-layer feature that is potentially valuable. In this work, we propose the Group-Transformer model (GTrans) that flexibly divides multi-layer representations of both encoder and decoder into different groups and then fuses these group features to generate target words. |
JIAN YANG et. al. | arxiv-cs.CL | 2022-07-29 |
| 125 | Multimodal Neural Machine Translation with Search Engine Based Image Retrieval Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an open-vocabulary image retrieval methods to collect descriptive images for bilingual parallel corpus using image search engine. |
ZhenHao Tang; XiaoBing Zhang; Zi Long; XiangHua Fu; | arxiv-cs.CV | 2022-07-26 |
| 126 | Lagrangian Method for Q-Function Learning (with Applications to Machine Translation) Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper discusses a new approach to the fundamental problem of learning optimal Q-functions. |
Huang Bojun; | arxiv-cs.LG | 2022-07-22 |
| 127 | Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore how we can endow robots with the ability to learn correspondences between their own skills, and those of morphologically different robots in different domains, in an entirely unsupervised manner. |
TANMAY SHANKAR et. al. | icml | 2022-07-15 |
| 128 | Directed Acyclic Transformer for Non-Autoregressive Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose Directed Acyclic Transfomer (DA-Transformer), which represents the hidden states in a Directed Acyclic Graph (DAG), where each path of the DAG corresponds to a specific translation. |
Fei Huang; Hao Zhou; Yang Liu; Hang Li; Minlie Huang; | icml | 2022-07-15 |
| 129 | Recent Advances in Retrieval-Augmented Text Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recently retrieval-augmented text generation has achieved state-of-the-art performance in many NLP tasks and has attracted increasing attention of the NLP and IR community, this tutorial thereby aims to present recent advances in retrieval-augmented text generation comprehensively and comparatively. |
Deng Cai; Yan Wang; Lemao Liu; Shuming Shi; | sigir | 2022-07-12 |
| 130 | Unifying Cross-lingual Summarization and Machine Translation with Compression Rate Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a novel task, Cross-lingual Summarization with Compression rate (CSC), to benefit Cross-Lingual Summarization by large-scale Machine Translation corpus. |
YU BAI et. al. | sigir | 2022-07-12 |
| 131 | No Language Left Behind: Scaling Human-Centered Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose multiple architectural and training improvements to counteract overfitting while training on thousands of tasks. |
NLLB TEAM et. al. | arxiv-cs.CL | 2022-07-11 |
| 132 | UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a novel method, named as Unified Multilingual Multiple teacher-student Model for NMT (UM4). |
JIAN YANG et. al. | arxiv-cs.CL | 2022-07-11 |
| 133 | HLT-MT: High-resource Language-specific Training for Multilingual Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference, which adopts the two-stage training with the language-specific selection mechanism. |
JIAN YANG et. al. | arxiv-cs.CL | 2022-07-11 |
| 134 | Non-Autoregressive Machine Translation: It’s Not As Fast As It Seems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we point out flaws in the evaluation methodology present in the literature on NAR models and we provide a fair comparison between a state-of-the-art NAR model and the autoregressive submissions to the shared task. |
Jindrich Helcl; Barry Haddow; Alexandra Birch; | naacl | 2022-07-09 |
| 135 | Tricks for Training Sparse Translation Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We find that that sparse architectures for multilingual machine translation can perform poorly out of the box and propose two straightforward techniques to mitigate this – a temperature heating mechanism and dense pre-training. |
DHEERU DUA et. al. | naacl | 2022-07-09 |
| 136 | Language Model Augmented Monotonic Attention for Simultaneous Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a framework to aid monotonic attention with an external language model to improve its decisions. |
Sathish Reddy Indurthi; Mohd Abbas Zaidi; Beomseok Lee; Nikhil Kumar Lakumarapu; Sangha Kim; | naacl | 2022-07-09 |
| 137 | Does Summary Evaluation Survive Translation to Other Languages? Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To investigate how much we can trust machine translation of summarization datasets, we translate the English SummEval dataset to seven languages and compare performances across automatic evaluation measures. |
Spencer Braun; Oleg Vasilyev; Neslihan Iskender; John Bohannon; | naacl | 2022-07-09 |
| 138 | Semantically Informed Slang Interpretation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a semantically informed slang interpretation (SSI) framework that considers jointly the contextual and semantic appropriateness of a candidate interpretation for a query slang. |
Zhewei Sun; Richard Zemel; Yang Xu; | naacl | 2022-07-09 |
| 139 | Original or Translated? A Causal Analysis of The Impact of Translationese on Machine Translation Performance Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we collect CausalMT, a dataset where the MT training data are also labeled with the human translation directions. |
Jingwei Ni; Zhijing Jin; Markus Freitag; Mrinmaya Sachan; Bernhard Sch?lkopf; | naacl | 2022-07-09 |
| 140 | Quality-Aware Decoding for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Despite the progress in machine translation quality estimation and evaluation in the last years, decoding in neural machine translation (NMT) is mostly oblivious to this and centers around finding the most probable translation according to the model (MAP decoding), approximated with beam search. In this paper, we bring together these two lines of research and propose quality-aware decoding for NMT, by leveraging recent breakthroughs in reference-free and reference-based MT evaluation through various inference methods like N-best reranking and minimum Bayes risk decoding. |
PATRICK FERNANDES et. al. | naacl | 2022-07-09 |
| 141 | Quantifying Synthesis and Fusion and Their Impact on Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, literature in Natural Language Processing (NLP) typically labels a whole language with a strict type of morphology, e.g. fusional or agglutinative. In this work, we propose to reduce the rigidity of such claims, by quantifying morphological typology at the word and segment level. |
ARTURO ONCEVAY et. al. | naacl | 2022-07-09 |
| 142 | On Systematic Style Differences Between Unsupervised and Supervised MT and An Application for High-Resource Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We compare translations from supervised and unsupervised MT systems of similar quality, finding that unsupervised output is more fluent and more structurally different in comparison to human translation than is supervised MT. We then demonstrate a way to combine the benefits of both methods into a single system which results in improved adequacy and fluency as rated by human evaluators. |
Kelly Marchisio; Markus Freitag; David Grangier; | naacl | 2022-07-09 |
| 143 | Building Multilingual Machine Translation Systems That Serve Arbitrary XY Translations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The model suffers from poor performance in one-to-many and many-to-many with zero-shot setup. To address this issue, this paper discusses how to practically build MNMT systems that serve arbitrary X-Y translation directions while leveraging multilinguality with a two-stage training strategy of pretraining and finetuning. |
Akiko Eriguchi; Shufang Xie; Tao Qin; Hany Hassan; | naacl | 2022-07-09 |
| 144 | The Devil Is in The Details: On The Pitfalls of Vocabulary Selection in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a model of vocabulary selection, integrated into the neural translation model, that predicts the set of allowed output words from contextualized encoder representations. |
TOBIAS DOMHAN et. al. | naacl | 2022-07-09 |
| 145 | High-resource Language-specific Training for Multilingual Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference, which adopts the two-stage training with the language-specific selection mechanism. |
JIAN YANG et. al. | ijcai | 2022-07-01 |
| 146 | Explicit Alignment Learning for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, we propose two approaches an explicit alignment learning approach, in which we further remove the need for the additional alignment model, and perform embedding mixup with the alignment based on encoder–decoder attention weights in the NMT model. |
Zuchao Li; Hai Zhao; Fengshun Xiao; Masao Utiyama; Eiichiro Sumita; | ijcai | 2022-07-01 |
| 147 | Reduce Indonesian Vocabularies with An Indonesian Sub-word Separator Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a strategy to address the unique word problem of the neural machine translation (NMT) system, which uses Indonesian as a pair language. |
Mukhlis Amien; Feng Chong; Huang Heyan; | arxiv-cs.CL | 2022-07-01 |
| 148 | Towards Discourse-Aware Document-Level Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim at incorporating the coherence information hidden within the RST-style discourse structure into machine translation. |
Xin Tan; Longyin Zhang; Fang Kong; Guodong Zhou; | ijcai | 2022-07-01 |
| 149 | AdMix: A Mixed Sample Data Augmentation Method for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel data augmentation approach for NMT, which is independent of any additional training data. |
Chang Jin; Shigui Qiu; Nini Xiao; Hao Jia; | ijcai | 2022-07-01 |
| 150 | Code Translation with Compiler Representations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we leverage low-level compiler intermediate representations (IR) to improve code translation. |
MARC SZAFRANIEC et. al. | arxiv-cs.PL | 2022-06-30 |
| 151 | GERNERMED++: Transfer Learning in German Medical NLP Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present a statistical model for German medical natural language processing trained for named entity recognition (NER) as an open, publicly available model. |
Johann Frei; Ludwig Frei-Stuber; Frank Kramer; | arxiv-cs.CL | 2022-06-29 |
| 152 | Building Multilingual Machine Translation Systems That Serve Arbitrary X-Y Translations Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The model suffers from poor performance in one-to-many and many-to-many with zero-shot setup. To address this issue, this paper discusses how to practically build MNMT systems that serve arbitrary X-Y translation directions while leveraging multilinguality with a two-stage training strategy of pretraining and finetuning. |
Akiko Eriguchi; Shufang Xie; Tao Qin; Hany Hassan Awadalla; | arxiv-cs.CL | 2022-06-29 |
| 153 | On The Impact of Noises in Crowd-Sourced Data for Speech Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: What are the impacts of these data quality issues for model development and evaluation? In this paper, we propose an automatic method to fix or filter the above quality issues, using English-German (En-De) translation as an example. |
Siqi Ouyang; Rong Ye; Lei Li; | arxiv-cs.CL | 2022-06-28 |
| 154 | Comparing Formulaic Language in Human and Machine Translation: Insight from A Parliamentary Corpus Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: A recent study has shown that, compared to human translations, neural machine translations contain more strongly-associated formulaic sequences made of relatively high-frequency words, but far less strongly-associated formulaic sequences made of relatively rare words. |
Yves Bestgen; | arxiv-cs.CL | 2022-06-22 |
| 155 | Scaling Autoregressive Models for Content-Rich Text-to-Image Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compositions and world knowledge. |
JIAHUI YU et. al. | arxiv-cs.CV | 2022-06-21 |
| 156 | The YiTrans End-to-End Speech Translation System for IWSLT 2022 Offline Shared Task Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper describes the submission of our end-to-end YiTrans speech translation system for the IWSLT 2022 offline task, which translates from English audio to German, Chinese, and Japanese. |
ZIQIANG ZHANG et. al. | arxiv-cs.CL | 2022-06-12 |
| 157 | A Novel Chinese Dialect TTS Frontend with Non-Autoregressive Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To lower the bar of use and make it more practical in commercial, we propose a novel Chinese dialect TTS frontend with a translation module. |
Wudi Bao; Junhui Zhang; Junjie Pan; Xiang Yin; Zejun Ma; | arxiv-cs.CL | 2022-06-10 |
| 158 | VALHALLA: Visual Hallucination for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce a visual hallucination framework, called VALHALLA, which requires only source sentences at inference time and instead uses hallucinated visual representations for multimodal machine translation. |
YI LI et. al. | cvpr | 2022-06-07 |
| 159 | Globetrotter: Connecting Languages By Connecting Images Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We introduce a method that uses visual observations to bridge the gap between languages, rather than relying on parallel corpora or topological properties of the representations. |
Dídac Surís; Dave Epstein; Carl Vondrick; | cvpr | 2022-06-07 |
| 160 | LegoNN: Building Modular Encoder-Decoder Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To achieve reusability, the interface between each encoder and decoder modules is grounded to a sequence of marginal distributions over a discrete vocabulary pre-defined by the model designer. We present two approaches for ingesting these marginals; one is differentiable, allowing the flow of gradients across the entire network, and the other is gradient-isolating. |
SIDDHARTH DALMIA et. al. | arxiv-cs.CL | 2022-06-07 |
| 161 | MorisienMT: A Dataset for Mauritian Creole Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe MorisienMT, a dataset for benchmarking machine translation quality of Mauritian Creole. |
Raj Dabre; Aneerav Sukhoo; | arxiv-cs.CL | 2022-06-06 |
| 162 | Finetuning A Kalaallisut-English Machine Translation System Using Web-crawled Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we attempt to finetune a pretrained Kalaallisut-to-English neural machine translation (NMT) system using web-crawled pseudoparallel sentences from around 30 multilingual websites. |
Alex Jones; | arxiv-cs.CL | 2022-06-05 |
| 163 | Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We find that for many-to-one translation we can indeed increase decoder speed without sacrificing quality using this approach, but for one-to-many translation, shallow decoders cause a clear quality drop. To ameliorate this drop, we propose a deep encoder with multiple shallow decoders (DEMSD) where each shallow decoder is responsible for a disjoint subset of target languages. |
XIANG KONG et. al. | arxiv-cs.CL | 2022-06-04 |
| 164 | Findings of The The RuATD Shared Task 2022 on Artificial Text Detection in Russian Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present the shared task on artificial text detection in Russian, which is organized as a part of the Dialogue Evaluation initiative, held in 2022. |
TATIANA SHAMARDINA et. al. | arxiv-cs.CL | 2022-06-03 |
| 165 | Exploring Diversity in Back Translation for Low-Resource Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This work puts forward a more nuanced framework for understanding diversity in training data, splitting it into lexical diversity and syntactic diversity. We present novel metrics for measuring these different aspects of diversity and carry out empirical analysis into the effect of these types of diversity on final neural machine translation model performance for low-resource English$\leftrightarrow$Turkish and mid-resource English$\leftrightarrow$Icelandic. |
Laurie Burchell; Alexandra Birch; Kenneth Heafield; | arxiv-cs.CL | 2022-06-01 |
| 166 | Refining Low-Resource Unsupervised Translation By Language Disentanglement of Multilingual Model Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose a simple refinement procedure to separate languages from a pre-trained multilingual UMT model for it to focus on only the target low-resource task. |
Xuan-Phi Nguyen; Shafiq Joty; Wu Kui; Ai Ti Aw; | arxiv-cs.CL | 2022-05-31 |
| 167 | VALHALLA: Visual Hallucination for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce a visual hallucination framework, called VALHALLA, which requires only source sentences at inference time and instead uses hallucinated visual representations for multimodal machine translation. |
YI LI et. al. | arxiv-cs.CV | 2022-05-31 |
| 168 | Preparing An Endangered Language for The Digital Age: The Case of Judeo-Spanish Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: For text-to-speech synthesis, we present a 3.5 hour single speaker speech corpus for building a neural speech synthesis engine. |
Alp Öktem; Rodolfo Zevallos; Yasmin Moslem; Güneş Öztürk; Karen Şarhon; | arxiv-cs.CL | 2022-05-31 |
| 169 | NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we focus on developing resources for languages in Indonesia. |
GENTA INDRA WINATA et. al. | arxiv-cs.CL | 2022-05-31 |
| 170 | X-SCITLDR: Cross-Lingual Extreme Summarization of Scholarly Documents Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we fill this research gap and present an abstractive cross-lingual summarization dataset for four different languages in the scholarly domain, which enables us to train and evaluate models that process English papers and generate summaries in German, Italian, Chinese and Japanese. |
Sotaro Takeshita; Tommaso Green; Niklas Friedrich; Kai Eckert; Simone Paolo Ponzetto; | arxiv-cs.CL | 2022-05-30 |
| 171 | Can Transformer Be Too Compositional? Analysing Idiom Processing in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we investigate whether the non-compositionality of idioms is reflected in the mechanics of the dominant NMT model, Transformer, by analysing the hidden states and attention patterns for models with English as source language and one of seven European languages as target language. |
Verna Dankers; Christopher G. Lucas; Ivan Titov; | arxiv-cs.CL | 2022-05-30 |
| 172 | CoNT: Contrastive Neural Text Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we analyse the underlying reasons and propose a new Contrastive Neural Text generation framework, CoNT. |
CHENXIN AN et. al. | arxiv-cs.CL | 2022-05-29 |
| 173 | BAN-Cap: A Multi-Purpose English-Bangla Image Descriptions Dataset Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: While most of the research attention is given to the English language in a monolingual setting, resource-constrained languages like Bangla remain out of focus, predominantly due to a lack of standard datasets. Addressing this issue, we present a new dataset BAN-Cap following the widely used Flickr8k dataset, where we collect Bangla captions of the images provided by qualified annotators. |
Mohammad Faiyaz Khan; S. M. Sadiq-Ur-Rahman Shifath; Md Saiful Islam; | arxiv-cs.CL | 2022-05-28 |
| 174 | Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate data augmentation techniques for synthesizing Dialectal Arabic-English CS text. |
Injy Hamed; Nizar Habash; Slim Abdennadher; Ngoc Thang Vu; | arxiv-cs.CL | 2022-05-25 |
| 175 | Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we explore the challenging problem of performing a generative task in a target language when labeled data is only available in English, using summarization as a case study. |
TU VU et. al. | arxiv-cs.CL | 2022-05-25 |
| 176 | FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide baselines for the tasks based on multilingual pre-trained models like mSLAM. |
ALEXIS CONNEAU et. al. | arxiv-cs.CL | 2022-05-24 |
| 177 | DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We introduce DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. |
Gabriele Sarti; Arianna Bisazza; Ana Guerberof Arenas; Antonio Toral; | arxiv-cs.CL | 2022-05-24 |
| 178 | T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new approach to perform zero-shot cross-modal transfer between speech and text for translation tasks. |
Paul-Ambroise Duquenne; Hongyu Gong; Benoît Sagot; Holger Schwenk; | arxiv-cs.CL | 2022-05-24 |
| 179 | Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: As an alternative, we propose performing back-translation via code summarization and generation. |
Wasi Uddin Ahmad; Saikat Chakraborty; Baishakhi Ray; Kai-Wei Chang; | arxiv-cs.CL | 2022-05-23 |
| 180 | A Template-based Method for Constrained Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose a template-based method that can yield results with high translation quality and match accuracy and the inference speed of our method is comparable with unconstrained NMT models. |
SHUO WANG et. al. | arxiv-cs.CL | 2022-05-23 |
| 181 | ISOMETRIC MT: Neural Machine Translation for Automatic Dubbing Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work introduces a self-learning approach that allows a transformer model to directly learn to generate outputs that closely match the source length, in short Isometric MT. In particular, our approach does not require to generate multiple hypotheses nor any auxiliary ranking function. |
S. M. Lakew; Y. Virkar; P. Mathur; M. Federico; | icassp | 2022-05-22 |
| 182 | How Sensitive Are Translation Systems to Extra Contexts? Mitigating Gender Bias in Neural Machine Translation Models Through Relevant Contexts Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: However, a growing number of studies also highlight the inherent gender bias that these models incorporate during training, which reflects poorly in their translations. In this work, we investigate whether these models can be instructed to fix their bias during inference using targeted, guided instructions as contexts. |
Shanya Sharma; Manan Dey; Koustuv Sinha; | arxiv-cs.CL | 2022-05-22 |
| 183 | Integrating Multiple ASR Systems Into NLP Backend with Attention Fusion Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we reduce the impact of ASR errors on the NLP back-end by combining transcriptions from various ASR systems. |
T. Kano; A. Ogawa; M. Delcroix; S. Watanabe; | icassp | 2022-05-22 |
| 184 | Context-Adaptive Document-Level Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work introduces a data-adaptive method that enables the model to adopt the necessary and helpful context. |
L. Zhang; Z. Zhang; B. Chen; W. Luo; L. Si; | icassp | 2022-05-22 |
| 185 | Tackling Data Scarcity in Speech Translation Using Zero-Shot Multilingual Machine Translation Techniques Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In the related field of multilingual text translation, several techniques have been proposed for zero-shot translation. |
T. A. Dinh; D. Liu; J. Niehues; | icassp | 2022-05-22 |
| 186 | Non-Autoregressive Neural Machine Translation: A Call for Clarity Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Non-autoregressive approaches aim to improve the inference speed of translation models by only requiring a single forward pass to generate the output sequence instead of iteratively producing each predicted token. |
Robin M. Schmidt; Telmo Pires; Stephan Peitz; Jonas Lööf; | arxiv-cs.CL | 2022-05-21 |
| 187 | SALTED: A Framework for SAlient Long-Tail Translation Error Detection Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Consequently, it is important to have visibility into these problems during model development. Towards this direction, we introduce SALTED, a specifications-based framework for behavioral testing of MT models that provides fine-grained views of salient long-tail errors, permitting trustworthy visibility into previously invisible problems. |
Vikas Raunak; Matt Post; Arul Menezes; | arxiv-cs.CL | 2022-05-20 |
| 188 | Understanding and Mitigating The Uncertainty in Zero-Shot Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to understand and alleviate the off-target issues from the perspective of uncertainty in zero-shot translation. |
Wenxuan Wang; Wenxiang Jiao; Shuo Wang; Zhaopeng Tu; Michael R. Lyu; | arxiv-cs.CL | 2022-05-20 |
| 189 | Translating Hanja Historical Documents to Contemporary Korean and English Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, we propose H2KE, a neural machine translation model, that translates historical documents in Hanja to more easily understandable Korean and to English. |
JUHEE SON et. al. | arxiv-cs.CL | 2022-05-20 |
| 190 | Data Augmentation to Address Out-of-Vocabulary Problem in Low-Resource Sinhala-English Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a word and phrase replacement-based DA technique that consider both types of OOV, by augmenting (1) rare words in the existing parallel corpus, and (2) new words from a bilingual dictionary. |
Aloka Fernando; Surangika Ranathunga; | arxiv-cs.CL | 2022-05-18 |
| 191 | Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we report our recent achievements in S2ST. |
QIANQIAN DONG et. al. | arxiv-cs.CL | 2022-05-18 |
| 192 | PreQuEL: Quality Estimation of Machine Translation Outputs in Advance Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the task of PreQuEL, Pre-(Quality-Estimation) Learning. |
Shachar Don-Yehiya; Leshem Choshen; Omri Abend; | arxiv-cs.CL | 2022-05-18 |
| 193 | Zero-Shot Cross-lingual Semantic Parsing Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a multi-task encoder-decoder model to transfer parsing knowledge to additional languages using only English-logical form paired data and in-domain natural language corpora in each new language. |
Tom Sherborne; Mirella Lapata; | acl | 2022-05-17 |
| 194 | Scheduled Multi-task Learning for Neural Chat Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Although the NCT models have achieved impressive success, it is still far from satisfactory due to insufficient chat translation data and simple joint training manners. To address the above issues, we propose a scheduled multi-task learning framework for NCT. |
Yunlong Liang; Fandong Meng; Jinan Xu; Yufeng Chen; Jie Zhou; | acl | 2022-05-17 |
| 195 | Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel posterior alignment technique that is truly online in its execution and superior in terms of alignment error rates compared to existing methods. |
Soumya Chatterjee; Sunita Sarawagi; Preethi Jyothi; | acl | 2022-05-17 |
| 196 | An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a framework for training non-autoregressive sequence-to-sequence models for editing tasks, where the original input sequence is iteratively edited to produce the output. |
Sweta Agrawal; Marine Carpuat; | acl | 2022-05-17 |
| 197 | Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: While one possible solution is to directly take target contexts into these statistical metrics, the target-context-aware statistical computing is extremely expensive, and the corresponding storage overhead is unrealistic. To solve the above issues, we propose a target-context-aware metric, named conditional bilingual mutual information (CBMI), which makes it feasible to supplement target context information for statistical metrics. |
SONGMING ZHANG et. al. | acl | 2022-05-17 |
| 198 | DEEP: DEnoising Entity Pre-training for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Earlier named entity translation methods mainly focus on phonetic transliteration, which ignores the sentence context for translation and is limited in domain and language coverage. To address this limitation, we propose DEEP, a DEnoising Entity Pre-training method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences. |
Junjie Hu; Hiroaki Hayashi; Kyunghyun Cho; Graham Neubig; | acl | 2022-05-17 |
| 199 | Efficient Cluster-Based K-Nearest-Neighbor Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To make it practical, in this paper, we explore a more efficient kNN-MT and propose to use clustering to improve the retrieval efficiency. |
Dexin Wang; Kai Fan; Boxing Chen; Deyi Xiong; | acl | 2022-05-17 |
| 200 | Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Confidence Based Bidirectional Global Context Aware (CBBGCA) training framework for NMT, where the NMT model is jointly trained with an auxiliary conditional masked language model (CMLM). |
CHULUN ZHOU et. al. | acl | 2022-05-17 |
| 201 | Consistent Human Evaluation of Machine Translation Across Language Pairs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new metric called XSTS that is more focused on semantic equivalence and a cross-lingual calibration method that enables more consistent assessment. |
DANIEL LICHT et. al. | arxiv-cs.CL | 2022-05-17 |
| 202 | Towards Making The Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper demonstrates that multilingual pretraining and multilingual fine-tuning are both critical for facilitating cross-lingual transfer in zero-shot translation, where the neural machine translation (NMT) model is tested on source languages unseen during supervised training. Following this idea, we present SixT+, a strong many-to-English NMT model that supports 100 source languages but is trained with a parallel dataset in only six source languages. |
GUANHUA CHEN et. al. | acl | 2022-05-17 |
| 203 | Neural Machine Translation with Phrase-Level Universal Visual Representations Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a phrase-level retrieval-based method for MMT to get visual information for the source input from existing sentence-image data sets so that MMT can break the limitation of paired sentence-image input. |
Qingkai Fang; Yang Feng; | acl | 2022-05-17 |
| 204 | UniTE: Unified Translation Evaluation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose , which is the first unified framework engaged with abilities to handle all three evaluation tasks. |
YU WAN et. al. | acl | 2022-05-17 |
| 205 | STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Existing techniques often attempt to transfer powerful machine translation (MT) capabilities to ST, but neglect the representation discrepancy across modalities. In this paper, we propose the Speech-TExt Manifold Mixup (STEMM) method to calibrate such discrepancy. |
Qingkai Fang; Rong Ye; Lei Li; Yang Feng; Mingxuan Wang; | acl | 2022-05-17 |
| 206 | Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. |
Minhan Xu; Yu Hong; | acl | 2022-05-17 |
| 207 | BiTIIMT: A Bilingual Text-infilling Method for Interactive Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel BiTIIMT system, Bilingual Text-Infilling for Interactive Neural Machine Translation. |
YANLING XIAO et. al. | acl | 2022-05-17 |
| 208 | On Vision Features in Multimodal Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we investigate the impact of vision models on MMT. |
BEI LI et. al. | acl | 2022-05-17 |
| 209 | Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce multilingual crossover encoder-decoder (mXEncDec) to fuse language pairs at an instance level. |
YONG CHENG et. al. | acl | 2022-05-17 |
| 210 | Learning Adaptive Segmentation Policy for End-to-End Simultaneous Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes an adaptive segmentation policy for end-to-end ST. Inspired by human interpreters, the policy learns to segment the source streaming speech into meaningful units by considering both acoustic features and translation history, maintaining consistency between the segmentation and translation. |
Ruiqing Zhang; Zhongjun He; Hua Wu; Haifeng Wang; | acl | 2022-05-17 |
| 211 | Measuring and Mitigating Name Biases in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we describe a new source of bias prevalent in NMT systems, relating to translations of sentences containing person names. |
Jun Wang; Benjamin Rubinstein; Trevor Cohn; | acl | 2022-05-17 |
| 212 | MSCTD: A Multimodal Sentiment Chat Translation Dataset Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we introduce a new task named Multimodal Chat Translation (MCT), aiming to generate more accurate translations with the help of the associated dialogue history and visual context. |
Yunlong Liang; Fandong Meng; Jinan Xu; Yufeng Chen; Jie Zhou; | acl | 2022-05-17 |
| 213 | Triangular Transfer: Freezing The Pivot for Triangular Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a transfer-learning-based approach that utilizes all types of auxiliary data. |
Meng Zhang; Liangyou Li; Qun Liu; | acl | 2022-05-17 |
| 214 | Machine Translation for Livonian: Catering to 20 Speakers Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we tackle the task of developing neural machine translation (NMT) between Livonian and English, with a two-fold aim: on one hand, preserving the language and on the other – enabling access to Livonian folklore, lifestories and other textual intangible heritage as well as making it easier to create further parallel corpora. |
Matiss Rikters; Marili Tomingas; Tuuli Tuisk; Valts Ern�treits; Mark Fishel; | acl | 2022-05-17 |
| 215 | Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we present a novel data augmentation paradigm termed Continuous Semantic Augmentation (CsaNMT), which augments each training instance with an adjacency semantic region that could cover adequate variants of literal expression under the same meaning. |
XIANGPENG WEI et. al. | acl | 2022-05-17 |
| 216 | ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper explores a deeper relationship between Transformer and numerical ODE methods. |
BEI LI et. al. | acl | 2022-05-17 |
| 217 | Can Transformer Be Too Compositional? Analysing Idiom Processing in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we investigate whether the non-compositionality of idioms is reflected in the mechanics of the dominant NMT model, Transformer, by analysing the hidden states and attention patterns for models with English as source language and one of seven European languages as target language. |
Verna Dankers; Christopher Lucas; Ivan Titov; | acl | 2022-05-17 |
| 218 | Redistributing Low-Frequency Words: Making The Most of Monolingual Data in Non-Autoregressive Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we provide an appealing alternative for NAT – monolingual KD, which trains NAT student on external monolingual data with AT teacher trained on the original bilingual data. |
Liang Ding; Longyue Wang; Shuming Shi; Dacheng Tao; Zhaopeng Tu; | acl | 2022-05-17 |
| 219 | DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present DiBiMT, the first entirely manually-curated evaluation benchmark which enables an extensive study of semantic biases in Machine Translation of nominal and verbal words in five different language combinations, namely, English and one or other of the following languages: Chinese, German, Italian, Russian and Spanish. |
Niccol� Campolungo; Federico Martelli; Francesco Saina; Roberto Navigli; | acl | 2022-05-17 |
| 220 | A Variational Hierarchical Model for Neural Cross-Lingual Summarization Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: However, it is very challenging for the model to directly conduct CLS as it requires both the abilities to translate and summarize. To address this issue, we propose a hierarchical model for the CLS task, based on the conditional variational auto-encoder. |
YUNLONG LIANG et. al. | acl | 2022-05-17 |
| 221 | Focus on The Target’s Vocabulary: Masked Label Smoothing for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: When allocating smoothed probability, original label smoothing treats the source-side words that would never appear in the target language equally to the real target-side words, which could bias the translation model. To address this issue, we propose Masked Label Smoothing (MLS), a new mechanism that masks the soft label probability of source-side words to zero. |
Liang Chen; Runxin Xu; Baobao Chang; | acl | 2022-05-17 |
| 222 | As Little As Possible, As Much As Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Omission and addition of content is a typical issue in neural machine translation. We propose a method for detecting such phenomena with off-the-shelf translation models. |
Jannis Vamvas; Rico Sennrich; | acl | 2022-05-17 |
| 223 | Geographical Distance Is The New Hyperparameter: A Case Study Of Finding The Optimal Pre-trained Language For English-isiZulu Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This study explores the potential benefits of transfer learning in an English-isiZulu translation framework. |
Muhammad Umair Nasir; Innocent Amos Mchechesi; | arxiv-cs.CL | 2022-05-17 |
| 224 | Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation (NMT). |
WENXUAN WANG et. al. | acl | 2022-05-17 |
| 225 | CipherDAug: Ciphertext Based Data Augmentation for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a novel data-augmentation technique for neural machine translation based on ROT-k ciphertexts. |
Nishant Kambhatla; Logan Born; Anoop Sarkar; | acl | 2022-05-17 |
| 226 | Bridging The Data Gap Between Training and Inference for Unsupervised Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To narrow the data gap, we propose an online self-training approach, which simultaneously uses the pseudo parallel data {natural source, translated target} to mimic the inference scenario. |
Zhiwei He; Xing Wang; Rui Wang; Shuming Shi; Zhaopeng Tu; | acl | 2022-05-17 |
| 227 | From Simultaneous to Streaming Machine Translation By Leveraging Streaming History Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a stream-level adaptation of the current latency measures based on a re-segmentation approach applied to the output translation, that is successfully evaluated on streaming conditions for a reference IWSLT task |
Javier Iranzo Sanchez; Jorge Civera; Alfons Juan-C�scar; | acl | 2022-05-17 |
| 228 | Bias Mitigation in Machine Translation Quality Estimation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We analyse the partial input bias in further detail and evaluate four approaches to use auxiliary tasks for bias mitigation. |
Hanna Behnke; Marina Fomicheva; Lucia Specia; | acl | 2022-05-17 |
| 229 | AppTek’s Submission to The IWSLT 2022 Isometric Spoken Language Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Abstract: To participate in the Isometric Spoken Language Translation Task of the IWSLT 2022 evaluation, constrained condition, AppTek developed neural Transformer-based systems for … |
Patrick Wilken; Evgeny Matusov; | arxiv-cs.CL | 2022-05-11 |
| 230 | Controlling Extra-Textual Attributes About Dialogue Participants — A Case Study of English-to-Polish Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We focus on the underresearched problem of utilising external metadata in automatic translation of TV dialogue, proposing a case study where a wide range of approaches for controlling attributes in translation is employed in a multi-attribute scenario. |
Sebastian T. Vincent; Loïc Barrault; Carolina Scarton; | arxiv-cs.CL | 2022-05-10 |
| 231 | ParaCotta: Synthetic Multilingual Paraphrase Corpora from The Most Diverse Translation Sample Pair Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We generate multiple translation samples using beam search and choose the most lexically diverse pair according to their sentence BLEU. |
ALHAM FIKRI AJI et. al. | arxiv-cs.CL | 2022-05-09 |
| 232 | CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We introduce an annotated dataset (CoCoA-MT) and an associated evaluation metric for training and evaluating formality-controlled MT models for six diverse target languages. |
MARIA NĂDEJDE et. al. | arxiv-cs.CL | 2022-05-09 |
| 233 | Example-Based Machine Translation from Text to A Hierarchical Representation of Sign Language Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article presents an original method for Text-to-Sign Translation. |
Élise Bertin-Lemée; Annelies Braffort; Camille Challant; Claire Danet; Michael Filhol; | arxiv-cs.CL | 2022-05-06 |
| 234 | Bridging The Domain Gap for Stance Detection for The Zulu Language Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a black-box non-intrusive method that utilizes techniques from Domain Adaptation to reduce the domain gap, without requiring any human expertise in the target language, by leveraging low-quality data in both a supervised and unsupervised manner. |
Gcinizwe Dlamini; Imad Eddine Ibrahim Bekkouch; Adil Khan; Leon Derczynski; | arxiv-cs.CL | 2022-05-06 |
| 235 | Non-Autoregressive Machine Translation: It’s Not As Fast As It Seems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we point out flaws in the evaluation methodology present in the literature on NAR models and we provide a fair comparison between a state-of-the-art NAR model and the autoregressive submissions to the shared task. |
Jindřich Helcl; Barry Haddow; Alexandra Birch; | arxiv-cs.CL | 2022-05-04 |
| 236 | ON-TRAC Consortium Systems for The IWSLT 2022 Dialect and Low-resource Speech Translation Tasks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2022: low-resource and dialect speech translation. |
MARCELY ZANON BOITO et. al. | arxiv-cs.CL | 2022-05-04 |
| 237 | Original or Translated? A Causal Analysis of The Impact of Translationese on Machine Translation Performance Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we collect CausalMT, a dataset where the MT training data are also labeled with the human translation directions. |
Jingwei Ni; Zhijing Jin; Markus Freitag; Mrinmaya Sachan; Bernhard Schölkopf; | arxiv-cs.CL | 2022-05-04 |
| 238 | Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Such methods may lose the information on the target side or have an increasing computational complexity as documents get longer. To address such problems, we introduce a recurrent memory unit to the vanilla Transformer, which supports the information exchange between the sentence and previous context. |
Yukun Feng; Feng Li; Ziang Song; Boyuan Zheng; Philipp Koehn; | arxiv-cs.AI | 2022-05-03 |
| 239 | The Implicit Length Bias of Label Smoothing on Beam Search Decoding Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We verify our theory by applying a simple rectification function at inference time to restore the unbiased distributions from the label-smoothed model predictions. |
Bowen Liang; Pidong Wang; Yuan Cao; | arxiv-cs.CL | 2022-05-02 |
| 240 | Quality-Aware Decoding for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Despite the progress in machine translation quality estimation and evaluation in the last years, decoding in neural machine translation (NMT) is mostly oblivious to this and centers around finding the most probable translation according to the model (MAP decoding), approximated with beam search. In this paper, we bring together these two lines of research and propose quality-aware decoding for NMT, by leveraging recent breakthroughs in reference-free and reference-based MT evaluation through various inference methods like $N$-best reranking and minimum Bayes risk decoding. |
PATRICK FERNANDES et. al. | arxiv-cs.CL | 2022-05-02 |
| 241 | Hausa Visual Genome: A Dataset for Multi-Modal English to Hausa Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, there is a need to create training and evaluation data for implementing machine learning tasks and bridging the research gap in the language. This work presents the Hausa Visual Genome (HaVG), a dataset that contains the description of an image or a section within the image in Hausa and its equivalent in English. |
IDRIS ABDULMUMIN et. al. | arxiv-cs.CL | 2022-05-02 |
| 242 | The Cross-lingual Conversation Summarization Challenge Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose the shared task of cross-lingual conversation summarization, \emph{ConvSumX Challenge}, opening new avenues for researchers to investigate solutions that integrate conversation summarization and machine translation. |
YULONG CHEN et. al. | arxiv-cs.CL | 2022-04-30 |
| 243 | How Robust Is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we analyze how translation performance changes as the data ratios among languages vary in the tokenizer training corpus. |
SHIYUE ZHANG et. al. | arxiv-cs.CL | 2022-04-29 |
| 244 | Can Machine Translation Be A Reasonable Alternative for Multilingual Question Answering Systems Over Knowledge Graphs? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we discuss Knowledge Graph Question Answering (KGQA) systems that aim at providing natural language access to data stored in Knowledge Graphs (KG). |
Aleksandr Perevalov; Andreas Both; Dennis Diefenbach; Axel-Cyrille Ngonga Ngomo; | www | 2022-04-29 |
| 245 | NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Translation-based similarity measures include direct and pivot translation probability, as well as translation cross-likelihood, which has not been studied so far. We analyze these measures in the common framework of multilingual NMT, releasing the NMTScore library (available at https://github.com/ZurichNLP/nmtscore). |
Jannis Vamvas; Rico Sennrich; | arxiv-cs.CL | 2022-04-28 |
| 246 | UniTE: Unified Translation Evaluation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose UniTE, which is the first unified framework engaged with abilities to handle all three evaluation tasks. |
YU WAN et. al. | arxiv-cs.CL | 2022-04-28 |
| 247 | When Do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a word-level contrastive objective to leverage word alignments for many-to-many NMT. |
ZHUOYUAN MAO et. al. | arxiv-cs.CL | 2022-04-26 |
| 248 | Data-Driven Adaptive Simultaneous Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, wait-k suffers from two major limitations: (a) it is a fixed policy that can not adaptively adjust latency given context, and (b) its training is much slower than full-sentence translation. To alleviate these issues, we propose a novel and efficient training scheme for adaptive SimulMT by augmenting the training corpus with adaptive prefix-to-prefix pairs, while the training complexity remains the same as that of training full-sentence translation models. |
GUANGXU XUN et. al. | arxiv-cs.CL | 2022-04-26 |
| 249 | Efficient Machine Translation Domain Adaptation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we explore several approaches to speed up nearest neighbor machine translation. |
Pedro Henrique Martins; Zita Marinho; André F. T. Martins; | arxiv-cs.CL | 2022-04-26 |
| 250 | A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we conduct a systematic survey with comparisons and discussions of various non-autoregressive translation (NAT) models from different aspects. |
YISHENG XIAO et. al. | arxiv-cs.CL | 2022-04-20 |
| 251 | IndicXNLI: Evaluating Multilingual Inference for Indian Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: While Indic NLP has made rapid advances recently in terms of the availability of corpora and pre-trained models, benchmark datasets on standard NLU tasks are limited. To this end, we introduce IndicXNLI, an NLI dataset for 11 Indic languages. |
Divyanshu Aggarwal; Vivek Gupta; Anoop Kunchukuttan; | arxiv-cs.CL | 2022-04-19 |
| 252 | PICT@DravidianLangTech-ACL2022: Neural Machine Translation On Dravidian Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a summary of the findings that we obtained based on the shared task on machine translation of Dravidian languages. |
Aditya Vyawahare; Rahul Tangsali; Aditya Mandke; Onkar Litake; Dipali Kadam; | arxiv-cs.CL | 2022-04-19 |
| 253 | Dynamic Position Encoding for Transformers Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, such embeddings are fixed after training regardless of the task and the word ordering system of the source or target language. In this paper, we propose a novel architecture with new position embeddings depending on the input text to address this shortcoming by taking the order of target words into consideration. |
Joyce Zheng; Mehdi Rezagholizadeh; Peyman Passban; | arxiv-cs.CL | 2022-04-17 |
| 254 | GLAD: Neural Predicate Synthesis to Repair Omission Faults Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: For template based approaches, omission faults provide no location to apply templates to; for learning based approaches that formulate repair as Neural Machine Translation (NMT), omission faults similarly do not provide the faulty code to translate. To address these issues, we propose GLAD, a novel learning-based repair technique that specifically targets if-clause synthesis. |
Sungmin Kang; Shin Yoo; | arxiv-cs.SE | 2022-04-14 |
| 255 | Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we present a novel data augmentation paradigm termed Continuous Semantic Augmentation (CsaNMT), which augments each training instance with an adjacency semantic region that could cover adequate variants of literal expression under the same meaning. |
XIANGPENG WEI et. al. | arxiv-cs.CL | 2022-04-14 |
| 256 | Creativity in Translation: Machine Translation As A Constraint for Literary Texts Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article presents the results of a study involving the translation of a short story by Kurt Vonnegut from English to Catalan and Dutch using three modalities: machine-translation (MT), post-editing (PE) and translation without aid (HT). |
Ana Guerberof Arenas; Antonio Toral; | arxiv-cs.CL | 2022-04-12 |
| 257 | ConSLT: A Token-level Contrastive Framework for Sign Language Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: SLT task is essentially a low-resource problem due to the scarcity of publicly available parallel data. To this end, inspired by the success of neural machine translation methods based on contrastive learning, we propose ConSLT, a novel token-level \textbf{Con}trastive learning framework for \textbf{S}ign \textbf{L}anguage \textbf{T}ranslation. |
BIAO FU et. al. | arxiv-cs.CL | 2022-04-11 |
| 258 | Large-Scale Streaming End-to-End Speech Translation with Neural Transducers Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce it to streaming end-to-end speech translation (ST), which aims to convert audio signals to texts in other languages directly. |
Jian Xue; Peidong Wang; Jinyu Li; Matt Post; Yashesh Gaur; | arxiv-cs.CL | 2022-04-11 |
| 259 | Toward More Effective Human Evaluation for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate a simple way to reduce cost by reducing the number of text segments that must be annotated in order to accurately predict a score for a complete test set. |
Belén Saldías; George Foster; Markus Freitag; Qijun Tan; | arxiv-cs.CL | 2022-04-11 |
| 260 | PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel machine translation-based approach, PharmMT, to automatically and reliably simplify prescription directions into patient-friendly language, thereby significantly reducing pharmacist workload. |
JIAZHAO LI et. al. | arxiv-cs.CL | 2022-04-08 |
| 261 | MMTAfrica: Multilingual Machine Translation for African Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we focus on the task of multilingual machine translation for African languages and describe our contribution in the 2021 WMT Shared Task: Large-Scale Multilingual Machine Translation. |
Chris C. Emezue; Bonaventure F. P. Dossou; | arxiv-cs.CL | 2022-04-08 |
| 262 | Towards Better Chinese-centric Neural Machine Translation for Low-resource Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we present the winner competition system that leverages monolingual word embeddings data enhancement, bilingual curriculum learning, and contrastive re-ranking. |
Bin Li; Yixuan Weng; Fei Xia; Hanjun Deng; | arxiv-cs.CL | 2022-04-08 |
| 263 | GigaST: A 10,000-hour Pseudo Speech Translation Corpus Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces GigaST, a large-scale pseudo speech translation (ST) corpus. |
RONG YE et. al. | arxiv-cs.CL | 2022-04-08 |
| 264 | Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists little parallel S2ST data, compared to the amount of data available for conventional cascaded systems that consist of automatic speech recognition (ASR), machine translation (MT), and text-to-speech (TTS) synthesis. In this work, we explore self-supervised pre-training with unlabeled speech data and data augmentation to tackle this issue. |
SRAVYA POPURI et. al. | arxiv-cs.CL | 2022-04-06 |
| 265 | Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we show that two parameter-efficient approaches to cross-lingual transfer, namely Sparse Fine-Tuning Masks (SFTMs) and Adapters, allow for a more lightweight and more effective zero-shot transfer to multilingual and cross-lingual retrieval tasks. |
Robert Litschko; Ivan Vulić; Goran Glavaš; | arxiv-cs.CL | 2022-04-05 |
| 266 | Modeling Target-Side Morphology in Neural Machine Translation: A Comparison of Strategies Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we re-investigate two target-side linguistic processing techniques: a lemma-tag strategy and a linguistically informed word segmentation strategy. |
Marion Weller-Di Marco; Matthias Huck; Alexander Fraser; | arxiv-cs.CL | 2022-03-25 |
| 267 | Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose an inference strategy to address this discrepancy. |
Sho Takase; Tatsuya Hiraoka; Naoaki Okazaki; | arxiv-cs.CL | 2022-03-25 |
| 268 | Mitigating Gender Bias in Machine Translation Through Adversarial Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an adversarial learning framework that addresses these challenges to mitigate gender bias in seq2seq machine translation. |
Eve Fleisig; Christiane Fellbaum; | arxiv-cs.CL | 2022-03-20 |
| 269 | Gaussian Multi-head Attention for Simultaneous Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose Gaussian Multi-head Attention (GMA) to develop a new SiMT policy by modeling alignment and translation in a unified manner. |
Shaolei Zhang; Yang Feng; | arxiv-cs.CL | 2022-03-17 |
| 270 | A Bayesian Approach to Translators’ Reliability Assessment Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the TQA as a complex process from the point of view of physics of complex systems and approach the reliability issue from the Bayesian paradigm. |
MARCO MICCHELI et. al. | arxiv-cs.CL | 2022-03-14 |
| 271 | A New Approach to Calculating BERTScore for Automatic Assessment of Translation Quality Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The study of the applicability of the BERTScore metric was conducted to translation quality assessment at the sentence level for English -> Russian direction. |
A. A. Vetrov; E. A. Gorn; | arxiv-cs.CL | 2022-03-10 |
| 272 | IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present the IndicNLG Benchmark, a collection of datasets for benchmarking NLG for 11 Indic languages. |
AMAN KUMAR et. al. | arxiv-cs.CL | 2022-03-10 |
| 273 | Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this problem, we propose a novel method, Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation(SBD-NMT). |
Xuanwei Zhang; Libin Shen; Disheng Pan; Liang Wang; Yanjun Miao; | arxiv-cs.CL | 2022-03-10 |
| 274 | Onception: Active Learning with Expert Advice for Real World Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this article, we assume a real world human-in-the-loop scenario in which: (i) the source sentences may not be readily available, but instead arrive in a stream; (ii) the automatic translations receive feedback in the form of a rating, instead of a correct/edited translation, since the human-in-the-loop might be a user looking for a translation, but not be able to provide one. |
Vânia Mendonça; Ricardo Rei; Luisa Coheur; Alberto Sardinha; | arxiv-cs.CL | 2022-03-08 |
| 275 | From Simultaneous to Streaming Machine Translation By Leveraging Streaming History Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, a state-of-the-art simultaneous sentence-level MT system is extended to the streaming setup by leveraging the streaming history. |
Javier Iranzo-Sánchez; Jorge Civera; Alfons Juan; | arxiv-cs.CL | 2022-03-04 |
| 276 | UDAAN: Machine Learning Based Post-Editing Tool for Document Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce UDAAN, an open-source post-editing tool that can reduce manual editing efforts to quickly produce publishable-standard documents in several Indic languages. |
Ayush Maheshwari; Ajay Ravindran; Venkatapathy Subramanian; Ganesh Ramakrishnan; | arxiv-cs.CL | 2022-03-03 |
| 277 | RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We argue that MBR still suffers from the following problems: The utility function only considers the lexical-level similarity between candidates; The expected utility considers the entire n-best list which is time-consuming and inadequate candidates in the tail list may hurt the performance; Only the relationship between candidates is considered. |
Yidan Zhang; Yu Wan; Dayiheng Liu; Baosong Yang; Zhenan He; | arxiv-cs.CL | 2022-02-28 |
| 278 | OCR Improves Machine Translation for Low-Resource Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We aim to investigate the performance of current OCR systems on low resource languages and low resource scripts. |
Oana Ignat; Jean Maillard; Vishrav Chaudhary; Francisco Guzmán; | arxiv-cs.CL | 2022-02-26 |
| 279 | The Reality of Multi-Lingual Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our book The Reality of Multi-Lingual Machine Translation discusses the benefits and perils of using more than two languages in machine translation systems. |
Tom Kocmi; Dominik Macháček; Ondřej Bojar; | arxiv-cs.CL | 2022-02-25 |
| 280 | JParaCrawl V3.0: A Large-scale English-Japanese Parallel Corpus Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Most current machine translation models are mainly trained with parallel corpora, and their translation accuracy largely depends on the quality and quantity of the corpora. |
Makoto Morishita; Katsuki Chousa; Jun Suzuki; Masaaki Nagata; | arxiv-cs.CL | 2022-02-25 |
| 281 | Screening Gender Transfer in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper aims at identifying the information flow in state-of-the-art machine translation systems, taking as example the transfer of gender when translating from French into English. |
Guillaume Wisniewski; Lichao Zhu; Nicolas Ballier; François Yvon; | arxiv-cs.CL | 2022-02-25 |
| 282 | Using Natural Language Prompts for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We explore the use of natural language prompts for controlling various aspects of the outputs generated by machine translation models. |
Xavier Garcia; Orhan Firat; | arxiv-cs.CL | 2022-02-23 |
| 283 | Refining The State-of-the-art in Machine Translation, Optimizing NMT for The JA <-> EN Language Pair By Leveraging Personal Domain Expertise Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Documenting the construction of an NMT (Neural Machine Translation) system for En/Ja based on the Transformer architecture leveraging the OpenNMT framework. |
Matthew Bieda; | arxiv-cs.CL | 2022-02-23 |
| 284 | An Overview on Machine Translation Evaluation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This report mainly includes the following contents: a brief history of machine translation evaluation (MTE), the classification of research methods on MTE, and the the cutting-edge progress, including human evaluation, automatic evaluation, and evaluation of evaluation methods (meta-evaluation). |
Lifeng Han; | arxiv-cs.CL | 2022-02-22 |
| 285 | Domain Adaptation in Neural Machine Translation Using A Qualia-Enriched FrameNet Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present Scylla, a methodology for domain adaptation of Neural Machine Translation (NMT) systems that make use of a multilingual FrameNet enriched with qualia relations as an external knowledge base. |
Alexandre Diniz Costa; Mateus Coutinho Marim; Ely Edison da Silva Matos; Tiago Timponi Torrent; | arxiv-cs.CL | 2022-02-21 |
| 286 | CALCS 2021 Shared Task: Machine Translation for Code-Switched Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address machine translation for code-switched social media data. |
Shuguang Chen; Gustavo Aguilar; Anirudh Srinivasan; Mona Diab; Thamar Solorio; | arxiv-cs.CL | 2022-02-19 |
| 287 | PETCI: A Parallel English Translation Dataset of Chinese Idioms Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present PETCI, a parallel English translation dataset of Chinese idioms, aiming to improve idiom translation by both human and machine. |
Kenan Tang; | arxiv-cs.CL | 2022-02-18 |
| 288 | Improving English to Sinhala Neural Machine Translation Using Part-of-Speech Tag Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, in this research, we explore effective methods of incorporating Part of Speech (POS) tags to the Transformer input embedding and positional encoding to further enhance the performance of the baseline English to Sinhala neural machine translation model. |
Ravinga Perera; Thilakshi Fonseka; Rashmini Naranpanawa; Uthayasanker Thayasivam; | arxiv-cs.CL | 2022-02-17 |
| 289 | End-to-End Training of Both Translation Models in The Back-Translation Framework Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a {\it categorical reparameterization trick} that makes NMT models generate {\it differentiable sentences}. |
DongNyeong Heo; Heeyoul Choi; | arxiv-cs.CL | 2022-02-17 |
| 290 | Sequence-to-Sequence Resources for Catalan Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we introduce sequence-to-sequence language resources for Catalan, a moderately under-resourced language, towards two tasks, namely: Summarization and Machine Translation (MT). |
Ona de Gibert; Ksenia Kharitonova; Blanca Calvo Figueras; Jordi Armengol-Estapé; Maite Melero; | arxiv-cs.CL | 2022-02-14 |
| 291 | Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a fine-tuning loss that enables pre-trained model’s ability to mine pseudo-parallel data for fully unsupervised machine translation. |
XUAN-PHI NGUYEN et. al. | iclr | 2022-02-08 |
| 292 | Non-Autoregressive Models Are Better Multilingual Translators Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose switch-GLAT, a non-autoregressive multilingual machine translation model with a code-switch decoder. |
ZHENQIAO SONG et. al. | iclr | 2022-02-08 |
| 293 | Deep Fusing Pre-trained Models Into Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework to deep fuse the pre-trained representation into NMT, fully exploring the potential of PTMs in NMT. |
Rongxiang Weng; Heng Yu; Weihua Luo; Min Zhang; | aaai | 2022-02-07 |
| 294 | From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Embedding matrices are key components in neural natural language processing (NLP) models that are responsible to provide numerical representations of input tokens (i.e. words or subwords). In this paper, we analyze the impact and utility of such matrices in the context of neural machine translation (NMT). |
Krtin Kumar; Peyman Passban; Mehdi Rezagholizadeh; Yiusing Lau; Qun Liu; | aaai | 2022-02-07 |
| 295 | Machine Translation from Signed to Spoken Languages: State of The Art and Challenges Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a systematic literature review to illustrate the state of the art in the domain and then, harking back to the requirements, lay out several challenges for future research. |
Mathieu De Coster; Dimitar Shterionov; Mieke Van Herreweghe; Joni Dambre; | arxiv-cs.CL | 2022-02-07 |
| 296 | Non-parametric Online Learning from Human Feedback for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a novel non-parametric online learning method without changing the model structure. |
DONGQI WANG et. al. | aaai | 2022-02-07 |
| 297 | Multilingual Code Snippets Training for Program Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce CoST, a new multilingual Code Snippet Translation dataset that contains parallel data from 7 commonly used programming languages. |
Ming Zhu; Karthik Suresh; Chandan K Reddy; | aaai | 2022-02-07 |
| 298 | Frequency-Aware Contrastive Learning for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we propose a frequency-aware token-level contrastive learning method, in which the hidden state of each decoding step is pushed away from the counterparts of other target words, in a soft contrastive way based on the corresponding word frequencies. |
TONG ZHANG et. al. | aaai | 2022-02-07 |
| 299 | Non-autoregressive Translation with Layer-Wise Prediction and Deep Supervision Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose DSLP, a highly efficient and high-performance model for machine translation. |
Chenyang Huang; Hao Zhou; Osmar R. Zaïane; Lili Mou; Lei Li; | aaai | 2022-02-07 |
| 300 | Pirá: A Bilingual Portuguese-English Dataset for Question-Answering About The Ocean Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the Pir\’a dataset, a large set of questions and answers about the ocean and the Brazilian coast both in Portuguese and English. |
ANDRÉ F. A. PASCHOAL et. al. | arxiv-cs.CL | 2022-02-04 |
| 301 | A Survey on Retrieval-Augmented Text Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper aims to conduct a survey about retrieval-augmented text generation. |
Huayang Li; Yixuan Su; Deng Cai; Yan Wang; Lemao Liu; | arxiv-cs.CL | 2022-02-02 |
| 302 | Anticipation-Free Training for Simultaneous Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This leads to aggressive anticipation during inference, resulting in the hallucination phenomenon. To mitigate this problem, we propose a new framework that decompose the translation process into the monotonic translation step and the reordering step, and we model the latter by the auxiliary sorting network (ASN). |
Chih-Chiang Chang; Shun-Po Chuang; Hung-yi Lee; | arxiv-cs.CL | 2022-01-30 |
| 303 | Prabhupadavani: A Code-mixed Speech Translation Data for 25 Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Thus, we introduce Prabhupadavani, which is a multilingual code-mixed ST dataset for 25 languages. |
Jivnesh Sandhan; Ayush Daksh; Om Adideva Paranjay; Laxmidhar Behera; Pawan Goyal; | arxiv-cs.CL | 2022-01-27 |
| 304 | Tackling Data Scarcity in Speech Translation Using Zero-shot Multilingual Machine Translation Techniques Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In the related field of multilingual text translation, several techniques have been proposed for zero-shot translation. |
Tu Anh Dinh; Danni Liu; Jan Niehues; | arxiv-cs.CL | 2022-01-26 |
| 305 | Supervised Visual Attention for Simultaneous Multimodal Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the first Transformer-based simultaneous MMT architecture, which has not been previously explored in the field. |
Veneta Haralampieva; Ozan Caglayan; Lucia Specia; | arxiv-cs.CL | 2022-01-23 |
| 306 | Linguistically-driven Multi-task Pre-training for Low-resource Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In the present study, we propose novel sequence-to-sequence pre-training objectives for low-resource machine translation (NMT): Japanese-specific sequence to sequence (JASS) for language pairs involving Japanese as the source or target language, and English-specific sequence to sequence (ENSS) for language pairs involving English. |
Zhuoyuan Mao; Chenhui Chu; Sadao Kurohashi; | arxiv-cs.CL | 2022-01-20 |
| 307 | VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Existing multimodal machine translation (MMT) datasets consist of images and video captions or general subtitles, which rarely contain linguistic ambiguity, making visual information not so effective to generate appropriate translations. We introduce VISA, a new dataset that consists of 40k Japanese-English parallel sentence pairs and corresponding video clips with the following key features: (1) the parallel sentences are subtitles from movies and TV episodes; (2) the source subtitles are ambiguous, which means they have multiple possible translations with different meanings; (3) we divide the dataset into Polysemy and Omission according to the cause of ambiguity. |
Yihang Li; Shuichiro Shimizu; Weiqi Gu; Chenhui Chu; Sadao Kurohashi; | arxiv-cs.CL | 2022-01-20 |
| 308 | Syntax-based Data Augmentation for Hungarian-English Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We train Transformer-based neural machine translation models for Hungarian-English and English-Hungarian using the Hunglish2 corpus. |
Attila Nagy; Patrick Nanys; Balázs Frey Konrád; Bence Bial; Judit Ács; | arxiv-cs.CL | 2022-01-18 |
| 309 | Improving Neural Machine Translation By Denoising Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a simple and effective pretraining strategy {D}en{o}ising {T}raining DoT for neural machine translation. |
Liang Ding; Keqin Peng; Dacheng Tao; | arxiv-cs.CL | 2022-01-18 |
| 310 | Klexikon: A German Dataset for Joint Summarization and Simplification Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Simultaneously, resources for non-English languages are scarce in general and prohibitive for training new solutions. To tackle this problem, we pose core requirements for a system that can jointly summarize and simplify long source documents. |
Dennis Aumiller; Michael Gertz; | arxiv-cs.CL | 2022-01-18 |
| 311 | Towards The Next 1000 Languages in Multilingual Machine Translation: Exploring The Synergy Between Supervised and Self-Supervised Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we present a pragmatic approach towards building a multilingual MT model that covers hundreds of languages, using a mixture of supervised and self-supervised objectives, depending on the data availability for different language pairs. |
ADITYA SIDDHANT et. al. | arxiv-cs.CL | 2022-01-09 |
| 312 | An Ensemble Approach to Acronym Extraction Using Transformers Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper discusses an ensemble approach for the task of Acronym Extraction, which utilises two different methods to extract acronyms and their corresponding long forms. |
Prashant Sharma; Hadeel Saadany; Leonardo Zilio; Diptesh Kanojia; Constantin Orăsan; | arxiv-cs.CL | 2022-01-09 |
| 313 | PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Phrase-level Adversarial Example Generation (PAEG) framework to enhance the robustness of the translation model. |
JUNCHENG WAN et. al. | arxiv-cs.CL | 2022-01-06 |
| 314 | SMDT: Selective Memory-Augmented Neural Document Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Selective Memory-augmented Neural Document Translation model to deal with documents containing large hypothesis space of the context. |
XU ZHANG et. al. | arxiv-cs.CL | 2022-01-05 |
| 315 | Integrating Deep Learning and Machine Translation for Understanding Unrefined Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details |
HongGeun Ji; Soyoung Oh; Jina Kim; Seong Choi; Eunil Park; | Computers, Materials & Continua | 2022-01-01 |
| 316 | How Do Lexical Semantics Affect Translation? An Empirical Study Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Here, we investigate these relationships on a variety of low-resource language pairs from the OpenSubtitles2016 database, where the source language is English, and find that the more similar the target language is to English, the greater the translation performance. |
Vivek Subramanian; Dhanasekar Sundararaman; | arxiv-cs.CL | 2021-12-31 |
| 317 | ViNMT: Neural Machine Translation Toolkit Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present an open-source toolkit for neural machine translation (NMT). |
NGUYEN HOANG QUAN et. al. | arxiv-cs.CL | 2021-12-30 |
| 318 | Pirá: A Bilingual Portuguese-English Dataset for Question-Answering About The Ocean Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the Pirá dataset, a large set of questions and answers about the ocean and the Brazilian coast both in Portuguese and English. |
ANDR&EACUTE; F. A. PASCHOAL et. al. | cikm | 2021-12-30 |
| 319 | QEMind: Alibaba’s Submission to The WMT21 Quality Estimation Shared Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present our submissions to the WMT 2021 QE shared task and an extensive set of experimental results have shown us that our multilingual systems outperform the best system in the Direct Assessment QE task of WMT 2020. |
JIAYI WANG et. al. | arxiv-cs.CL | 2021-12-29 |
| 320 | A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to augment attention based neural network with reordering information to alleviate the lack of data. |
Mohaddeseh Bastan; Shahram Khadivi; | arxiv-cs.CL | 2021-12-27 |
| 321 | HOPE: A Task-Oriented and Human-Centric Evaluation Framework Using Professional Post-Editing Towards More Effective MT Evaluation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we introduce HOPE, a task-oriented and human-centric evaluation framework for machine translation output based on professional post-editing annotations. |
Serge Gladkoff; Lifeng Han; | arxiv-cs.CL | 2021-12-27 |
| 322 | Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we demonstrate the use of cross-lingual word embeddings for detecting cognates among fourteen Indian Languages. |
DIPTESH KANOJIA et. al. | arxiv-cs.CL | 2021-12-16 |
| 323 | Learning and Analyzing Generation Order for Undirected Sequence Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we train a policy that learns the generation order for a pre-trained, undirected translation model via reinforcement learning. |
Yichen Jiang; Mohit Bansal; | arxiv-cs.CL | 2021-12-16 |
| 324 | Isometric MT: Neural Machine Translation for Automatic Dubbing Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work introduces a self-learning approach that allows a transformer model to directly learn to generate outputs that closely match the source length, in short Isometric MT. In particular, our approach does not require to generate multiple hypotheses nor any auxiliary ranking function. |
Surafel M. Lakew; Yogesh Virkar; Prashant Mathur; Marcello Federico; | arxiv-cs.CL | 2021-12-16 |
| 325 | Lesan — Machine Translation for Low Resource Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Lesan, an MT system for low resource languages. |
Asmelash Teka Hadgu; Abel Aregawi; Adam Beaudoin; | arxiv-cs.CL | 2021-12-15 |
| 326 | Isochrony-Aware Neural Machine Translation for Automatic Dubbing Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose implicit and explicit modeling approaches to integrate isochrony information into neural machine translation. |
Derek Tam; Surafel M. Lakew; Yogesh Virkar; Prashant Mathur; Marcello Federico; | arxiv-cs.CL | 2021-12-15 |
| 327 | Improving Both Domain Robustness and Domain Adaptability in Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a novel approach, RMLNMT (Robust Meta-Learning Framework for Neural Machine Translation Domain Adaptation), which improves the robustness of existing meta-learning models. |
Wen Lai; Jindřich Libovický; Alexander Fraser; | arxiv-cs.CL | 2021-12-15 |
| 328 | Step-unrolled Denoising Autoencoders for Text Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper we propose a new generative model of text, Step-unrolled Denoising Autoencoder (SUNDAE), that does not rely on autoregressive models. |
Nikolay Savinov; Junyoung Chung; Mikolaj Binkowski; Erich Elsen; Aaron van den Oord; | arxiv-cs.CL | 2021-12-13 |
| 329 | Communication-Efficient Federated Learning for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore how to efficiently build NMT models in an FL setup by proposing a novel solution. |
Tanya Roosta; Peyman Passban; Ankit Chadha; | arxiv-cs.CL | 2021-12-11 |
| 330 | Selecting Parallel In-domain Sentences for Neural Machine Translation Using Monolingual Texts Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Specific use-cases are usually left out, since generic models tend to perform poorly in domain-specific cases. |
Javad Pourmostafa Roshan Sharami; Dimitar Shterionov; Pieter Spronck; | arxiv-cs.CL | 2021-12-11 |
| 331 | Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To address this issue, we propose a novel GAN model, i.e., AU-GAN, which has an asymmetric architecture for adverse domain translation. |
JEONG-GI KWAK et. al. | arxiv-cs.CV | 2021-12-08 |
| 332 | Multitask Finetuning for Improving Neural Machine Translation in Indian Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a Multitask Finetuning methodology which combines the Bilingual Machine Translation task with an auxiliary Causal Language Modeling task to improve performance on the former task on Indian Languages. |
Shaily Desai; Atharva Kshirsagar; Manisha Marathe; | arxiv-cs.CL | 2021-12-03 |
| 333 | Translating Politeness Across Cultures: Case of Hindi and English Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a corpus based study of politeness across two languages-English and Hindi. |
Ritesh Kumar; Girish Nath Jha; | arxiv-cs.CL | 2021-12-03 |
| 334 | Improvement in Machine Translation with Generative Adversarial Networks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore machine translation improvement via Generative Adversarial Network (GAN) architecture. |
Jay Ahn; Hari Madhu; Viet Nguyen; | arxiv-cs.CL | 2021-11-30 |
| 335 | Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes our submission to the constrained track of WMT21 shared news translation task. |
AMR HENDY et. al. | arxiv-cs.CL | 2021-11-25 |
| 336 | Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a parameter-free, Dependency-scaled Self-Attention Network (Deps-SAN) for syntax-aware Transformer-based NMT. |
RU PENG et. al. | arxiv-cs.CL | 2021-11-23 |
| 337 | BARTScore: Evaluating Generated Text As Text Generation IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we conceptualize the evaluation of generated text as a text generation problem, modeled using pre-trained sequence-to-sequence models. |
Weizhe Yuan; Graham Neubig; Pengfei Liu; | nips | 2021-11-20 |
| 338 | R-Drop: Regularized Dropout for Neural Networks IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce a simple consistency training strategy to regularize dropout, namely R-Drop, which forces the output distributions of different sub models generated by dropout to be consistent with each other. |
XIAOBO LIANG et. al. | nips | 2021-11-20 |
| 339 | Data Processing Matters: SRPH-Konvergen AI’s Machine Translation System for WMT’21 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe the submission of the joint Samsung Research Philippines-Konvergen AI team for the WMT’21 Large Scale Multilingual Translation Task – Small Track 2. |
Lintang Sutawika; Jan Christian Blaise Cruz; | arxiv-cs.CL | 2021-11-19 |
| 340 | XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. |
ARUN BABU et. al. | arxiv-cs.CL | 2021-11-17 |
| 341 | High Quality Rather Than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In Neural Machine Translation, it is typically assumed that the sentence with the highest estimated probability should also be the translation with the highest quality as measured by humans. In this work, we question this assumption and show that model estimates and translation quality only vaguely correlate. |
Markus Freitag; David Grangier; Qijun Tan; Bowen Liang; | arxiv-cs.CL | 2021-11-17 |
| 342 | NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper provides an overview of NVIDIA NeMo’s neural machine translation systems for the constrained data track of the WMT21 News and Biomedical Shared Translation Tasks. |
Sandeep Subramanian; Oleksii Hrinchuk; Virginia Adams; Oleksii Kuchaiev; | arxiv-cs.CL | 2021-11-16 |
| 343 | Measuring Uncertainty in Translation Quality Evaluation (TQE) Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: The methodology we applied for this work is from Bernoulli Statistical Distribution Modelling (BSDM) and Monte Carlo Sampling Analysis (MCSA). |
Serge Gladkoff; Irina Sorokina; Lifeng Han; Alexandra Alekseeva; | arxiv-cs.CL | 2021-11-15 |
| 344 | Sign Language Translation with Hierarchical Spatio-TemporalGraph Neural Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, these unique characteristics of sign languages are formulated as hierarchical spatio-temporal graph representations, including high-level and fine-level graphs of which a vertex characterizes a specified body part and an edge represents their interactions. |
JICHAO KAN et. al. | arxiv-cs.CV | 2021-11-14 |
| 345 | BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In our work, we propose instead, to refine the mined bitexts via automatic editing: given a sentence in a language xf, and a possibly imperfect translation of it xe, our model generates a revised version xf’ or xe’ that yields a more equivalent translation pair (i.e., |
Eleftheria Briakou; Sida I. Wang; Luke Zettlemoyer; Marjan Ghazvininejad; | arxiv-cs.CL | 2021-11-12 |
| 346 | Speeding Up Entmax Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: $\alpha$-entmax of Peters et al. (2019, arXiv:1905.05702) solves this problem, but is considerably slower than softmax. In this paper, we propose an alternative to $\alpha$-entmax, which keeps its virtuous characteristics, but is as fast as optimized softmax and achieves on par or better performance in machine translation task. |
Maxat Tezekbayev; Vassilina Nikoulina; Matthias Gallé; Zhenisbek Assylbekov; | arxiv-cs.CL | 2021-11-12 |
| 347 | Variance-Aware Machine Translation Test Sets Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We release 70 small and discriminative test sets for machine translation (MT) evaluation called variance-aware test sets (VAT), covering 35 translation directions from WMT16 to WMT20 competitions. |
Runzhe Zhan; Xuebo Liu; Derek F. Wong; Lidia S. Chao; | arxiv-cs.CL | 2021-11-07 |
| 348 | Developing Neural Machine Translation Models for Hungarian-English Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: I propose 5 different augmentation methods that are structure-aware, meaning that instead of randomly selecting words for blanking or replacement, the dependency tree of sentences is used as a basis for augmentation. |
Attila Nagy; | arxiv-cs.CL | 2021-11-07 |
| 349 | BERT, MBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we demonstrate that simply using the output (contextualized embeddings) of a tailored and suitable bilingual pre-trained language model (dubbed BiBERT) as the input of the NMT encoder achieves state-of-the-art translation performance. |
Haoran Xu; Benjamin Van Durme; Kenton Murray; | emnlp | 2021-11-05 |
| 350 | Improving The Quality Trade-Off for Neural Machine Translation Multi-Domain Adaptation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study this problem in an adaptation setting where the goal is to preserve the existing system quality while incorporating data for domains that were not the focus of the original translation system. |
EVA HASLER et. al. | emnlp | 2021-11-05 |
| 351 | Cross Attention Augmented Transducer Networks for Simultaneous Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper proposes a novel architecture, Cross Attention Augmented Transducer (CAAT), for simultaneous translation. |
Dan Liu; Mengge Du; Xiaoxi Li; Ya Li; Enhong Chen; | emnlp | 2021-11-05 |
| 352 | Evaluating The Morphosyntactic Well-formedness of Generated Texts Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose L’AMBRE – a metric to evaluate the morphosyntactic well-formedness of text using its dependency parse and morphosyntactic rules of the language. |
ADITHYA PRATAPA et. al. | emnlp | 2021-11-05 |
| 353 | Cross-Attention Is All You Need: Adapting Pretrained Transformers for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. |
Mozhdeh Gheini; Xiang Ren; Jonathan May; | emnlp | 2021-11-05 |
| 354 | Learning to Rewrite for Non-Autoregressive Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose an architecture named RewriteNAT to explicitly learn to rewrite the erroneous translation pieces. |
Xinwei Geng; Xiaocheng Feng; Bing Qin; | emnlp | 2021-11-05 |
| 355 | Rule-based Morphological Inflection Improves Neural Terminology Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce a modular framework for incorporating lemma constraints in neural MT (NMT) in which linguistic knowledge and diverse types of NMT models can be flexibly applied. |
Weijia Xu; Marine Carpuat; | emnlp | 2021-11-05 |
| 356 | Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a redundant head enlivening (RHE) method to precisely identify redundant heads, and then vitalize their potential by learning syntactic relations and prior knowledge in the text without sacrificing the roles of important heads. |
Tianfu Zhang; Heyan Huang; Chong Feng; Longbing Cao; | emnlp | 2021-11-05 |
| 357 | A Generative Framework for Simultaneous Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a generative framework for simultaneous machine translation. |
Yishu Miao; Phil Blunsom; Lucia Specia; | emnlp | 2021-11-05 |
| 358 | Wikily Supervised Neural Translation Tailored to Cross-Lingual Tasks Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a simple but effective approach for leveraging Wikipedia for neural machine translation as well as cross-lingual tasks of image captioning and dependency parsing without using any direct supervision from external parallel data or supervised models in the target language. |
Mohammad Sadegh Rasooli; Chris Callison-Burch; Derry Tanti Wijaya; | emnlp | 2021-11-05 |
| 359 | Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we present a qualitative study that examines the role of datasets in stimulating the leverage of visual modality and we propose methods to highlight the importance of visual signals in the datasets which demonstrate improvements in reliance of models on the source images. |
Jiaoda Li; Duygu Ataman; Rico Sennrich; | emnlp | 2021-11-05 |
| 360 | Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose heterogeneous ways of embedding topic information at the sentence level into an NMT model to improve translation performance. |
Weixuan Wang; Wei Peng; Meng Zhang; Qun Liu; | emnlp | 2021-11-05 |
| 361 | Towards Making The Most of Dialogue Characteristics for Neural Chat Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose to promote the chat translation by introducing the modeling of dialogue characteristics into the NCT model. |
YUNLONG LIANG et. al. | emnlp | 2021-11-05 |
| 362 | Translation-based Supervision for Policy Generation in Simultaneous Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a novel supervised learning approach for training an agent that can detect the minimum number of reads required for generating each target token by comparing simultaneous translations against full-sentence translations during training to generate oracle action sequences. |
Ashkan Alinejad; Hassan S. Shavarani; Anoop Sarkar; | emnlp | 2021-11-05 |
| 363 | Distributionally Robust Multilingual Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a new learning objective for MNMT based on distributionally robust optimization, which minimizes the worst-case expected loss over the set of language pairs. |
Chunting Zhou; Daniel Levy; Xian Li; Marjan Ghazvininejad; Graham Neubig; | emnlp | 2021-11-05 |
| 364 | One Source, Two Targets: Challenges and Rewards of Dual Decoding Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the other. |
Jitao Xu; Fran?ois Yvon; | emnlp | 2021-11-05 |
| 365 | GFST: Gender-Filtered Self-Training for More Accurate Gender in Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose gender-filtered self-training (GFST) to improve gender translation accuracy on unambiguously gendered inputs. |
Prafulla Kumar Choubey; Anna Currey; Prashant Mathur; Georgiana Dinu; | emnlp | 2021-11-05 |
| 366 | Neural Machine Translation Quality and Post-Editing Performance Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Across all models, we found that better MT systems indeed lead to fewer changes in the sentences in this industry setting. |
Vil?m Zouhar; Martin Popel; Ondrej Bojar; Ale? Tamchyna; | emnlp | 2021-11-05 |
| 367 | AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To tackle these challenges, we propose AfroMT, a standardized, clean, and reproducible machine translation benchmark for eight widely spoken African languages. |
Machel Reid; Junjie Hu; Graham Neubig; Yutaka Matsuo; | emnlp | 2021-11-05 |
| 368 | I Wish I Would Have Loved This One, But I Didn’t – A Multilingual Dataset for Counterfactual Detection in Product Review Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of counterfactual detection (CFD) in product reviews. |
James O?Neill; Polina Rozenshtein; Ryuichi Kiryo; Motoko Kubota; Danushka Bollegala; | emnlp | 2021-11-05 |
| 369 | Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose a cross-lingual data selection method to extract in-domain sentences in the missing language side from a large generic monolingual corpus. |
Thuy-Trang Vu; Xuanli He; Dinh Phung; Gholamreza Haffari; | emnlp | 2021-11-05 |
| 370 | Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose to follow a completely different approach and present a multi-task DA approach in which we generate new sentence pairs with transformations, such as reversing the order of the target sentence, which produce unfluent target sentences. |
V?ctor M. S?nchez-Cartagena; Miquel Espl?-Gomis; Juan Antonio P?rez-Ortiz; Felipe S?nchez-Mart?nez; | emnlp | 2021-11-05 |
| 371 | Cross-lingual Intermediate Fine-tuning Improves Dialogue State Tracking Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we enhance the transfer learning process by intermediate fine-tuning of pretrained multilingual models, where the multilingual models are fine-tuned with different but related data and/or tasks. |
Nikita Moghe; Mark Steedman; Alexandra Birch; | emnlp | 2021-11-05 |
| 372 | Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This work presents Wino-X, a parallel dataset of German, French, and Russian schemas, aligned with their English counterparts. |
Denis Emelin; Rico Sennrich; | emnlp | 2021-11-05 |
| 373 | Improving Neural Machine Translation By Bidirectional Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a simple and effective pretraining strategy – bidirectional training (BiT) for neural machine translation. |
Liang Ding; Di Wu; Dacheng Tao; | emnlp | 2021-11-05 |
| 374 | An Empirical Investigation of Word Alignment Supervision for Zero-Shot Multilingual Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the benefits of an explicit alignment to language labels in Transformer-based MNMT models in the zero-shot context, by jointly training one cross attention head with word alignment supervision to stress the focus on the target language label. |
Alessandro Raganato; Ra?l V?zquez; Mathias Creutz; J?rg Tiedemann; | emnlp | 2021-11-05 |
| 375 | Recurrent Attention for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we push further in this research line and propose a novel substitute mechanism for self-attention: Recurrent AtteNtion (RAN) . |
Jiali Zeng; Shuangzhi Wu; Yongjing Yin; Yufan Jiang; Mu Li; | emnlp | 2021-11-05 |
| 376 | It Is Not As Good As You Think! Evaluating Simultaneous Machine Translation on Interpretation Data Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In the absence of interpretation training data, we propose a translation-to-interpretation (T2I) style transfer method which allows converting existing offline translations into interpretation-style data, leading to up-to 2.8 BLEU improvement. |
Jinming Zhao; Philip Arthur; Gholamreza Haffari; Trevor Cohn; Ehsan Shareghi; | emnlp | 2021-11-05 |
| 377 | Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we apply one translation per discourse in NMT, and aim to encourage lexical translation consistency for document-level NMT. |
Xinglin Lyu; Junhui Li; Zhengxian Gong; Min Zhang; | emnlp | 2021-11-05 |
| 378 | Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an approach, MultiUAT, that dynamically adjusts the training data usage based on the model’s uncertainty on a small set of trusted clean data for multi-corpus machine translation. |
MINGHAO WU et. al. | emnlp | 2021-11-05 |
| 379 | Language Modeling, Lexical Translation, Reordering: The Training Process of NMT Through The Lens of Classical SMT Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we look at the competences related to three core SMT components and find that during training, NMT first focuses on learning target-side language modeling, then improves translation quality approaching word-by-word translation, and finally learns more complicated reordering patterns. |
Elena Voita; Rico Sennrich; Ivan Titov; | emnlp | 2021-11-05 |
| 380 | AligNART: Non-autoregressive Neural Machine Translation By Jointly Learning to Estimate Alignment and Translate Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce AligNART, which leverages full alignment information to explicitly reduce the modality of the target distribution. |
Jongyoon Song; Sungwon Kim; Sungroh Yoon; | emnlp | 2021-11-05 |
| 381 | Don’t Go Far Off: An Empirical Study on Neural Poetry Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present an empirical investigation for poetry translation along several dimensions: 1) size and style of training data (poetic vs. non-poetic), including a zero-shot setup; 2) bilingual vs. multilingual learning; and 3) language-family-specific models vs. mixed-language-family models. |
Tuhin Chakrabarty; Arkadiy Saakyan; Smaranda Muresan; | emnlp | 2021-11-05 |
| 382 | Translating Headers of Tabular Data: A Pilot Study of Schema Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To facilitate the research study, we construct the first parallel dataset for schema translation, which consists of 3,158 tables with 11,979 headers written in 6 different languages, including English, Chinese, French, German, Spanish, and Japanese. Also, we propose the first schema translation model called CAST, which is a header-to-header neural machine translation model augmented with schema context. |
Kunrui Zhu; Yan Gao; Jiaqi Guo; Jian-Guang Lou; | emnlp | 2021-11-05 |
| 383 | XLEnt: Mining A Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose Lexical-Semantic-Phonetic Align (LSP-Align), a technique to automatically mine cross-lingual entity lexica from mined web data. |
Ahmed El-Kishky; Adithya Renduchintala; James Cross; Francisco Guzm?n; Philipp Koehn; | emnlp | 2021-11-05 |
| 384 | BiSECT: Learning to Split and Rephrase Sentences with Bitexts Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We introduce a novel dataset and a new model for this ‘split and rephrase’ task. |
Joongwon Kim; Mounica Maddela; Reno Kriz; Wei Xu; Chris Callison-Burch; | emnlp | 2021-11-05 |
| 385 | Document Graph for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we hypothesize that a document can be represented as a graph that connects relevant contexts regardless of their distances. |
Mingzhou Xu; Liangyou Li; Derek F. Wong; Qun Liu; Lidia S. Chao; | emnlp | 2021-11-05 |
| 386 | HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To improve effectiveness of the available BT data, we introduce HintedBT-a family of techniques which provides hints (through tags) to the encoder and decoder. |
Sahana Ramnath; Melvin Johnson; Abhirut Gupta; Aravindan Raghuveer; | emnlp | 2021-11-05 |
| 387 | PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We introduce a high-quality and large-scale Vietnamese-English parallel dataset of 3.02M sentence pairs, which is 2.9M pairs larger than the benchmark Vietnamese-English machine translation corpus IWSLT15. |
Long Doan; Linh The Nguyen; Nguyen Luong Tran; Thai Hoang; Dat Quoc Nguyen; | emnlp | 2021-11-05 |
| 388 | Unsupervised Neural Machine Translation with Universal Grammar Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, in this paper, we seek to leverage such shared grammar clues to provide more explicit language parallel signals to enhance the training of unsupervised machine translation models. |
Zuchao Li; Masao Utiyama; Eiichiro Sumita; Hai Zhao; | emnlp | 2021-11-05 |
| 389 | Mutual-Learning Improves End-to-End Speech Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an alternative-a trainable mutual-learning scenario, where the MT and the ST models are collaboratively trained and are considered as peers, rather than teacher/student. |
Jiawei Zhao; Wei Luo; Boxing Chen; Andrew Gilman; | emnlp | 2021-11-05 |
| 390 | MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we improve multilingual text-to-text transfer Transformer with translation pairs (mT6). |
ZEWEN CHI et. al. | emnlp | 2021-11-05 |
| 391 | Data and Parameter Scaling Laws for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We observe that the development cross-entropy loss of supervised neural machine translation models scales like a power law with the amount of training data and the number of non-embedding parameters in the model. |
Mitchell A Gordon; Kevin Duh; Jared Kaplan; | emnlp | 2021-11-05 |
| 392 | Controlling Machine Translation for Multiple Attributes with Additive Interventions Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address these problems by introducing vector-valued interventions which allow for fine-grained control over multiple attributes simultaneously via a weighted linear combination of the corresponding vectors. |
Andrea Schioppa; David Vilar; Artem Sokolov; Katja Filippova; | emnlp | 2021-11-05 |
| 393 | Reducing The Impact of Out of Vocabulary Words in The Translation of Natural Language Questions Into SPARQL Queries Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we combine Named Entity Linking, Named Entity Recognition, and Neural Machine Translation to perform automatic translation of natural language questions into SPARQL queries. |
Manuel A. Borroto Santana; Francesco Ricca; Bernardo Cuteri; | arxiv-cs.CL | 2021-11-04 |
| 394 | Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This report describes Microsoft’s machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. |
JIAN YANG et. al. | arxiv-cs.CL | 2021-11-03 |
| 395 | Lingua Custodia’s Participation at The WMT 2021 Machine Translation Using Terminologies Shared Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes Lingua Custodia’s submission to the WMT21 shared task on machine translation using terminologies. |
Melissa Ailem; Jinghsu Liu; Raheel Qader; | arxiv-cs.CL | 2021-11-03 |
| 396 | Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose automatic translation of dialogue datasets with alignment to ensure faithful translation of slot values and eliminate costly human supervision used in previous benchmarks. Finally, we present RiSAWOZ English and German datasets, created using our translation methodology. |
Mehrad Moradshahi; Victoria Tsai; Giovanni Campagna; Monica S. Lam; | arxiv-cs.CL | 2021-11-03 |
| 397 | Quality Estimation Using Round-trip Translation with Sentence Embeddings Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit round-trip translation, proposing a system which aims to solve the previous pitfalls found with the approach. |
Nathan Crone; Adam Power; John Weldon; | arxiv-cs.CL | 2021-10-31 |
| 398 | How Should Human Translation Coexist with NMT? Efficient Tool for Building High Quality Parallel Corpus Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a tool for efficiently constructing high-quality parallel corpora with minimizing human labor and making this tool publicly available. |
CHANJUN PARK et. al. | arxiv-cs.CL | 2021-10-30 |
| 399 | Simultaneous Neural Machine Translation with Constituent Label Prediction Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the concept of pre-reordering, we propose a couple of simple decision rules using the label of the next constituent predicted by incremental constituent label prediction. |
Yasumasa Kano; Katsuhito Sudoh; Satoshi Nakamura; | arxiv-cs.CL | 2021-10-26 |
| 400 | Assessing Evaluation Metrics for Speech-to-Speech Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Abstract: Speech-to-speech translation combines machine translation with speech synthesis, introducing evaluation challenges not present in either task alone. How to automatically evaluate … |
Elizabeth Salesky; Julian Mäder; Severin Klinger; | arxiv-cs.CL | 2021-10-26 |
| 401 | Noisy UGC Translation at The Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This work explores the capacities of character-based Neural Machine Translation to translate noisy User-Generated Content (UGC) with a strong focus on exploring the limits of such approaches to handle productive UGC phenomena, which almost by definition, cannot be seen at training time. |
José Carlos Rosales Núñez; Guillaume Wisniewski; Djamé Seddah; | arxiv-cs.CL | 2021-10-24 |
| 402 | Discontinuous Grammar As A Foreign Language Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To close the gap, we here extend the framework of sequence-to-sequence models for constituent parsing, not only by providing a more powerful neural architecture for improving their performance, but also by enlarging their coverage to handle the most complex syntactic phenomena: discontinuous structures. |
Daniel Fernández-González; Carlos Gómez-Rodríguez; | arxiv-cs.CL | 2021-10-20 |
| 403 | Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we thus propose an algorithm to reorder and refine the target side of a full sentence translation corpus, so that the words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. |
HYOJUNG HAN et. al. | arxiv-cs.CL | 2021-10-18 |
| 404 | The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new corpus for gender identification and rewriting in contexts involving one or two target users (I and/or You) — first and second grammatical persons with independent grammatical gender preferences. |
Bashar Alhafni; Nizar Habash; Houda Bouamor; | arxiv-cs.CL | 2021-10-18 |
| 405 | Towards Making The Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper demonstrates that multilingual pretraining and multilingual fine-tuning are both critical for facilitating cross-lingual transfer in zero-shot translation, where the neural machine translation (NMT) model is tested on source languages unseen during supervised training. Following this idea, we present SixT+, a strong many-to-English NMT model that supports 100 source languages but is trained with a parallel dataset in only six source languages. |
GUANHUA CHEN et. al. | arxiv-cs.CL | 2021-10-16 |
| 406 | Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Hierarchical Knowledge Distillation (HKD) approach for MNMT which capitalises on language groups generated according to typological features and phylogeny of languages to overcome the issue of negative transfer. |
Fahimeh Saleh; Wray Buntine; Gholamreza Haffari; Lan Du; | arxiv-cs.CL | 2021-10-14 |
| 407 | Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose DSLP, a highly efficient and high-performance model for machine translation. |
Chenyang Huang; Hao Zhou; Osmar R. Zaïane; Lili Mou; Lei Li; | arxiv-cs.CL | 2021-10-14 |
| 408 | Decision Attentive Regularization to Improve Simultaneous Speech Translation Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Decision Attentive Regularization (DAR) to improve the decision policy of SimulST systems by using the simultaneous text-to-text translation (SimulMT) task. |
Mohd Abbas Zaidi; Beomseok Lee; Sangha Kim; Chanwoo Kim; | arxiv-cs.SD | 2021-10-13 |
| 409 | Evaluation of Abstractive Summarisation Models with Machine Translation in Deliberative Processes Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present work on summarising deliberative processes for non-English languages. |
M. Arana-Catania; Rob Procter; Yulan He; Maria Liakata; | arxiv-cs.CL | 2021-10-12 |
| 410 | Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To generate such samples, we propose a doubly-trained architecture that pairs two NMT models of opposite translation directions with a joint loss function, which combines the target-side attack and the source-side semantic similarity constraint. |
Weiting Tan; Shuoyang Ding; Huda Khayrallah; Philipp Koehn; | arxiv-cs.CL | 2021-10-11 |
| 411 | Using Document Similarity Methods to Create Parallel Datasets for Code Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to use document similarity methods to create noisy parallel datasets of code, thus enabling supervised techniques to be applied for automated code translation without having to rely on the availability or expensive curation of parallel code datasets. |
MAYANK AGARWAL et. al. | arxiv-cs.CL | 2021-10-11 |
| 412 | Unsupervised Neural Machine Translation with Generative Language Models Only Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. |
JESSE MICHAEL HAN et. al. | arxiv-cs.CL | 2021-10-11 |
| 413 | WeTS: A Benchmark for Translation Suggestion Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: With the corpus we construct, we introduce the Transformer-based model for TS, and experimental results show that our model achieves State-Of-The-Art (SOTA) results on all four translation directions, including English-to-German, German-to-English, Chinese-to-English and English-to-Chinese. |
Zhen Yang; Fandong Meng; Yingxue Zhang; Ernan Li; Jie Zhou; | arxiv-cs.CL | 2021-10-11 |
| 414 | SurfaceNet: Adversarial SVBRDF Estimation From A Single Image Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper we present SurfaceNet, an approach for estimating spatially-varying bidirectional reflectance distribution function (SVBRDF) material properties from a single image. |
Giuseppe Vecchio; Simone Palazzo; Concetto Spampinato; | iccv | 2021-10-08 |
| 415 | Machine Translation Verbosity Control for Automatic Dubbing Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the problem of controlling the verbosity of machine translation output, so that subsequent steps of our automatic dubbing pipeline can generate dubs of better quality. |
SURAFEL M. LAKEW et. al. | arxiv-cs.CL | 2021-10-07 |
| 416 | On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. |
Gal Patel; Leshem Choshen; Omri Abend; | arxiv-cs.CL | 2021-10-06 |
| 417 | The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we instead consider the impact of compression in a data-limited regime. |
Orevaoghene Ahia; Julia Kreutzer; Sara Hooker; | arxiv-cs.CL | 2021-10-06 |
| 418 | SDA-GAN: Unsupervised Image Translation Using Spectral Domain Attention-Guided Generative Adversarial Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work introduced a novel GAN architecture for unsupervised image translation on the task of face style transform. |
Qizhou Wang; Maksim Makarenko; | arxiv-cs.CV | 2021-10-06 |
| 419 | Sequence-to-Sequence Lexical Normalization with Multilingual Transformers Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a sentence-level sequence-to-sequence model based on mBART, which frames the problem as a machine translation problem. |
Ana-Maria Bucur; Adrian Cosma; Liviu P. Dinu; | arxiv-cs.CL | 2021-10-06 |
| 420 | On The Complementarity Between Pre-Training and Back-Translation for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We introduce two probing tasks for PT and BT respectively and find that PT mainly contributes to the encoder module while BT brings more benefits to the decoder. |
XUEBO LIU et. al. | arxiv-cs.CL | 2021-10-05 |
| 421 | Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the tagged-multilingual NMT model and improve the self-learning algorithm to handle these two problems. |
Chenyang Li; Gongxu Luo; | arxiv-cs.CL | 2021-10-01 |
| 422 | Sentiment-Aware Measure (SAM) for Evaluating Sentiment Transfer By Machine Translation Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a numerical `sentiment-closeness’ measure appropriate for assessing the accuracy of a translated affect message in UGC text by an MT system. |
Hadeel Saadany; Constantin Orasan; Emad Mohamed; Ashraf Tantawy; | arxiv-cs.CL | 2021-09-30 |
| 423 | BLEU, METEOR, BERTScore: Evaluation of Metrics Performance in Assessing Critical Translation Errors in Sentiment-oriented Text Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we assess the ability of automatic quality metrics to detect critical machine translation errors which can cause serious misunderstanding of the affect message. |
Hadeel Saadany; Constantin Orasan; | arxiv-cs.CL | 2021-09-29 |
| 424 | EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe the EdinSaar submission to the shared task of Multilingual Low-Resource Translation for North Germanic Languages at the Sixth Conference on Machine Translation (WMT2021). |
Svetlana Tchistiakova; Jesujoba Alabi; Koel Dutta Chowdhury; Sourav Dutta; Dana Ruiter; | arxiv-cs.CL | 2021-09-29 |
| 425 | Text Simplification for Comprehension-based Question-Answering Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we investigate the effect of text simplification in the task of question-answering using a comprehension context. |
Tanvi Dadu; Kartikey Pant; Seema Nagar; Ferdous Ahmed Barbhuiya; Kuntal Dey; | arxiv-cs.CL | 2021-09-28 |
| 426 | Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a cascaded model based on the non-autoregressive Transformer that enables end-to-end training without the need for an explicit intermediate representation. |
EVGENIIA TOKARCHUK et. al. | arxiv-cs.CL | 2021-09-27 |
| 427 | Towards Reinforcement Learning for Pivot-based Neural Machine Translation with Non-autoregressive Transformer Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We utilize a non-autoregressive transformer and present an end-to-end pivot-based integrated model, enabling training on source-target data. |
EVGENIIA TOKARCHUK et. al. | arxiv-cs.CL | 2021-09-27 |
| 428 | Unsupervised Translation of German–Lower Sorbian: Exploring Training and Novel Transfer Methods on A Low-Resource Language Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2021 Unsupervised Machine Translation task for German–Lower Sorbian (DE–DSB): a high-resource language to a low-resource one. |
Lukas Edman; Ahmet Üstün; Antonio Toral; Gertjan van Noord; | arxiv-cs.CL | 2021-09-24 |
| 429 | Faithful Target Attribute Prediction in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We argue that predicting the target word and attributes simultaneously is an effective way to ensure that translations are more faithful to the training data distribution with respect to these attributes. |
Xing Niu; Georgiana Dinu; Prashant Mathur; Anna Currey; | arxiv-cs.CL | 2021-09-24 |
| 430 | Exploiting Curriculum Learning in Unsupervised Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To address this problem, we propose a curriculum learning method to gradually utilize pseudo bi-texts based on their quality from multiple granularities. |
Jinliang Lu; Jiajun Zhang; | arxiv-cs.CL | 2021-09-23 |
| 431 | The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes the Volctrans’ submission to the WMT21 news translation shared task for German->English translation. |
LIHUA QIAN et. al. | arxiv-cs.CL | 2021-09-23 |
| 432 | The NiuTrans Machine Translation Systems for WMT21 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes NiuTrans neural machine translation systems of the WMT 2021 news translation tasks. |
SHUHAN ZHOU et. al. | arxiv-cs.CL | 2021-09-21 |
| 433 | Learning Kernel-Smoothed Machine Translation with Retrieved Examples Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER), an effective approach to adapt neural machine translation models online. |
QINGNAN JIANG et. al. | arxiv-cs.CL | 2021-09-21 |
| 434 | One Source, Two Targets: Challenges and Rewards of Dual Decoding Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the other. |
Jitao Xu; François Yvon; | arxiv-cs.CL | 2021-09-21 |
| 435 | TranslateLocally: Blazing-fast Translation Running on The Local CPU Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bring control back to the end user and demonstrate speed, we developed translateLocally. |
Nikolay Bogoychev; Jelmer Van der Linde; Kenneth Heafield; | arxiv-cs.CL | 2021-09-21 |
| 436 | CUNI Systems for WMT21: Terminology Translation Shared Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes Charles University submission for Terminology translation Shared Task at WMT21. |
Josef Jon; Michal Novák; João Paulo Aires; Dušan Variš; Ondřej Bojar; | arxiv-cs.CL | 2021-09-20 |
| 437 | The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the JHU-Microsoft joint submission for WMT 2021 quality estimation shared task. |
Shuoyang Ding; Marcin Junczys-Dowmunt; Matt Post; Christian Federmann; Philipp Koehn; | arxiv-cs.CL | 2021-09-17 |
| 438 | Back-translation for Large-Scale Multilingual Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This work aims to build a single multilingual translation system with a hypothesis that a universal cross-language representation leads to better multilingual translation performance. |
Baohao Liao; Shahram Khadivi; Sanjika Hewavitharana; | arxiv-cs.CL | 2021-09-17 |
| 439 | Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend the definition of glass-box QE generally to uncertainty quantification with both black-box and glass-box approaches and design several features deduced from them to blaze a new trial in improving QE’s performance. |
KE WANG et. al. | arxiv-cs.CL | 2021-09-15 |
| 440 | Miðeind’s WMT 2021 Submission Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Mi{\dh}eind’s submission for the English$\to$Icelandic and Icelandic$\to$English subsets of the 2021 WMT news translation task. |
Haukur Barri Símonarson; Vésteinn Snæbjarnarson; Pétur Orri Ragnarsson; Haukur Páll Jónsson; Vilhjálmur Þorsteinsson; | arxiv-cs.CL | 2021-09-15 |
| 441 | When Does Translation Require Context? A Data-driven, Multilingual Exploration Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new metric, P-CXMI, which allows us to identify translations that require context systematically and confirm the difficulty of previously studied phenomena as well as uncover new ones that have not been addressed in previous work. We then develop the Multilingual Discourse-Aware (MuDA) benchmark, a series of taggers for these phenomena in 14 different language pairs, which we use to evaluate context-aware MT. We find that state-of-the-art context-aware MT models find marginal improvements over context-agnostic models on our benchmark, which suggests current models do not handle these ambiguities effectively. We release code and data to invite the MT research community to increase efforts on context-aware translation on discourse phenomena and languages that are currently overlooked. |
Kayo Yin; Patrick Fernandes; André F. T. Martins; Graham Neubig; | arxiv-cs.CL | 2021-09-15 |
| 442 | Sequence Length Is A Domain: Length-based Overfitting in Transformer Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present results which suggest that the issue might also be in the mismatch between the length distributions of the training and validation data combined with the aforementioned tendency of the neural networks to overfit to the training data. |
Dušan Variš; Ondřej Bojar; | arxiv-cs.CL | 2021-09-15 |
| 443 | Netmarble AI Center’s WMT21 Automatic Post-Editing Shared Task Submission Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes Netmarble’s submission to WMT21 Automatic Post-Editing (APE) Shared Task for the English-German language pair. |
Shinhyeok Oh; Sion Jang; Hu Xu; Shounan An; Insoo Oh; | arxiv-cs.CL | 2021-09-14 |
| 444 | Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for $k$-nearest-neighbor retrieval. |
XIN ZHENG et. al. | arxiv-cs.CL | 2021-09-14 |
| 445 | Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Information Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose CorefCL, a novel data augmentation and contrastive learning scheme based on coreference between the source and contextual sentences. |
Yongkeun Hwang; Hyungu Yun; Kyomin Jung; | arxiv-cs.CL | 2021-09-13 |
| 446 | Uncertainty-Aware Machine Translation Evaluation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce uncertainty-aware MT evaluation and analyze the trustworthiness of the predicted quality. |
Taisiya Glushkova; Chrysoula Zerva; Ricardo Rei; André F. T. Martins; | arxiv-cs.CL | 2021-09-13 |
| 447 | Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a universal SiMT model with Mixture-of-Experts Wait-k Policy to achieve the best translation quality under arbitrary latency with only one trained model. |
Shaolei Zhang; Yang Feng; | arxiv-cs.CL | 2021-09-11 |
| 448 | Improving Multilingual Translation By Representation and Gradient Regularization Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we observe that off-target translation is dominant even in strong multilingual systems, trained on massive multilingual corpora. |
YILIN YANG et. al. | arxiv-cs.CL | 2021-09-10 |
| 449 | Neural Machine Translation Quality and Post-Editing Performance Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Across all models, we found that better MT systems indeed lead to fewer changes in the sentences in this industry setting. |
Vilém Zouhar; Aleš Tamchyna; Martin Popel; Ondřej Bojar; | arxiv-cs.CL | 2021-09-10 |
| 450 | Rethinking Zero-shot Neural Machine Translation: From A Perspective of Latent Variables Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce a denoising autoencoder objective based on pivot language into traditional training objective to improve the translation accuracy on zero-shot directions. |
WEIZHI WANG et. al. | arxiv-cs.CL | 2021-09-10 |
| 451 | Dynamic Terminology Integration for COVID-19 and Other Emerging Domains Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work is part of WMT2021 Shared Task: Machine Translation using Terminologies, where we describe Tilde MT systems that are capable of dynamic terminology integration at the time of translation. |
Toms Bergmanis; Mārcis Pinnis; | arxiv-cs.CL | 2021-09-10 |
| 452 | Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose to follow a completely different approach and present a multi-task DA approach in which we generate new sentence pairs with transformations, such as reversing the order of the target sentence, which produce unfluent target sentences. |
Víctor M. Sánchez-Cartagena; Miquel Esplà-Gomis; Juan Antonio Pérez-Ortiz; Felipe Sánchez-Martínez; | arxiv-cs.CL | 2021-09-08 |
| 453 | Collecting A Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we find grammatical patterns indicating stereotypical and non-stereotypical gender-role assignments (e.g., female nurses versus male dancers) in corpora from three domains, resulting in a first large-scale gender bias dataset of 108K diverse real-world English sentences. |
Shahar Levy; Koren Lazar; Gabriel Stanovsky; | arxiv-cs.CL | 2021-09-08 |
| 454 | Ensemble Fine-tuned MBERT for Translation Quality Estimation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we discuss our submission to the WMT 2021 QE Shared Task. |
Shaika Chowdhury; Naouel Baili; Brian Vannah; | arxiv-cs.CL | 2021-09-08 |
| 455 | Competence-based Curriculum Learning for Multilingual Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we focus on balancing the learning competencies of different languages and propose Competence-based Curriculum Learning for Multilingual Machine Translation, named CCL-M. |
Mingliang Zhang; Fandong Meng; Yunhai Tong; Jie Zhou; | arxiv-cs.CL | 2021-09-08 |
| 456 | IndicBART: A Pre-trained Model for Indic Natural Language Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we study pre-trained sequence-to-sequence models for a group of related languages, with a focus on Indic languages. |
RAJ DABRE et. al. | arxiv-cs.CL | 2021-09-07 |
| 457 | Mixup Decoding for Diverse Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Leveraging the linear relationship in the sentence latent space introduced by the mixup training, we propose a novel method, MixDiversity, to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus when decoding. |
JICHENG LI et. al. | arxiv-cs.CL | 2021-09-07 |
| 458 | Revisiting Context Choices for Context-aware Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that multi-source transformer models improve MT over standard transformer-base models even with empty lines provided as context, but the translation quality improves significantly (1.51 – 2.65 BLEU) when a sufficient amount of correct context is provided. |
Matīss Rikters; Toshiaki Nakazawa; | arxiv-cs.CL | 2021-09-07 |
| 459 | Paraphrase Generation As Unsupervised Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new paradigm for paraphrase generation by treating the task as unsupervised machine translation (UMT) based on the assumption that there must be pairs of sentences expressing the same meaning in a large-scale unlabeled monolingual corpus. |
XIAOFEI SUN et. al. | arxiv-cs.CL | 2021-09-07 |
| 460 | Infusing Future Information Into Monotonic Attention Through Language Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Simultaneous neural machine translation(SNMT) models start emitting the target sequence before they have processed the source sequence. |
Mohd Abbas Zaidi; Sathish Indurthi; Beomseok Lee; Nikhil Kumar Lakumarapu; Sangha Kim; | arxiv-cs.CL | 2021-09-07 |
| 461 | Transformer Models for Text Coherence Assessment Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Accordingly, in this paper, we propose four different Transformer-based architectures for the task: vanilla Transformer, hierarchical Transformer, multi-task learning-based model, and a model with fact-based input representation. |
Tushar Abhishek; Daksh Rawat; Manish Gupta; Vasudeva Varma; | arxiv-cs.CL | 2021-09-05 |
| 462 | How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology? Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We find that learning to analyse and generate morphologically complex surface representations is still challenging, especially for non-concatenative morphological phenomena like reduplication or vowel harmony and for rare word stems. |
Chantal Amrhein; Rico Sennrich; | arxiv-cs.CL | 2021-09-02 |
| 463 | Masked Adversarial Generation for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the Masked Adversarial Generation (MAG) model, that learns to perturb the translation model throughout the training process. |
Badr Youbi Idrissi; Stéphane Clinchant; | arxiv-cs.CL | 2021-09-01 |
| 464 | Survey of Low-Resource Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a survey covering the state of the art in low-resource machine translation research. |
Barry Haddow; Rachel Bawden; Antonio Valerio Miceli Barone; Jindřich Helcl; Alexandra Birch; | arxiv-cs.CL | 2021-09-01 |
| 465 | MMARCO: A Multilingual Version of The MS MARCO Passage Ranking Dataset Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we present mMARCO, a multilingual version of the MS MARCO passage ranking dataset comprising 13 languages that was created using machine translation. |
LUIZ BONIFACIO et. al. | arxiv-cs.CL | 2021-08-31 |
| 466 | An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We propose an unsupervised method to build SS corpora from large-scale bilingual translation corpora, alleviating the need for SS supervised corpora. By taking the pair of the source sentences of translation corpus and the translations of their references in a bridge language, we can construct large-scale pseudo parallel SS data. |
Xinyu Lu; Jipeng Qiang; Yun Li; Yunhao Yuan; Yi Zhu; | arxiv-cs.CL | 2021-08-31 |
| 467 | Secoco: Self-Correcting Encoding for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors. |
TAO WANG et. al. | arxiv-cs.CL | 2021-08-27 |
| 468 | Position-Invariant Truecasing with A Word-and-Character Hierarchical Recurrent Neural Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a fast, accurate and compact two-level hierarchical word-and-character-based recurrent neural network model, the first of its kind for this problem. |
Hao Zhang; You-Chi Cheng; Shankar Kumar; Mingqing Chen; Rajiv Mathews; | arxiv-cs.CL | 2021-08-26 |
| 469 | Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To effectively learn semantic alignments among product images and bilingual texts in translation, we design a unified product-oriented cross-modal cross-lingual model (\upoc~) for pre-training and fine-tuning. In this paper, we first construct a large-scale bilingual product description dataset called Fashion-MMT, which contains over 114k noisy and 40k manually cleaned description translations with multiple product images. We will release the dataset and codes at https://github.com/syuqings/Fashion-MMT. |
YUQING SONG et. al. | arxiv-cs.CV | 2021-08-25 |
| 470 | Examining Covert Gender Bias: A Case Study in Turkish and English Machine Translation Models Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Specifically, we introduce a method to investigate asymmetrical gender markings. |
Chloe Ciora; Nur Iren; Malihe Alikhani; | arxiv-cs.CL | 2021-08-23 |
| 471 | Recurrent Multiple Shared Layers in Depth for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to train a deeper model with recurrent mechanism, which loops the encoder and decoder blocks of Transformer in the depth direction. |
GuoLiang Li; Yiyang Li; | arxiv-cs.CL | 2021-08-23 |
| 472 | Attentive Fine-tuning of Transformers for Translation of Low-resourced Languages @LoResMT 2021 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: This paper reports the Machine Translation (MT) systems submitted by the IIITT team for the English->Marathi and English->Irish language pairs LoResMT 2021 shared task. |
KARTHIK PURANIK et. al. | arxiv-cs.CL | 2021-08-19 |
| 473 | Active Learning for Massively Parallel Translation of Constrained Text Into Low Resource Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an algorithm for human and machine to work together seamlessly to translate a closed text into a severely low resource language. |
Zhong Zhou; Alex Waibel; | arxiv-cs.CL | 2021-08-16 |
| 474 | Findings of The LoResMT 2021 Shared Task on COVID and Sign Language for Low-resource Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the findings of the LoResMT 2021 shared task which focuses on machine translation (MT) of COVID-19 data for both low-resource spoken and sign languages. |
ATUL KR. OJHA et. al. | arxiv-cs.CL | 2021-08-14 |
| 475 | A Survey on Low-Resource Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a survey for low-resource NMT and classify related works into three categories according to the auxiliary data they used: (1) exploiting monolingual data of source and/or target languages, (2) exploiting data from auxiliary languages, and (3) exploiting multi-modal data. |
Rui Wang; Xu Tan; Renqian Luo; Tao Qin; Tie-Yan Liu; | ijcai | 2021-08-13 |
| 476 | Improving Context-Aware Neural Machine Translation with Source-side Monolingual Documents Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To make full use of source-side monolingual documents for context-aware NMT, we propose a Pre-training approach with Global Context (PGC). |
LINQING CHEN et. al. | ijcai | 2021-08-13 |
| 477 | Automatically Paraphrasing Via Sentence Reconstruction and Round-trip Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework for paraphrase generation. |
ZILU GUO et. al. | ijcai | 2021-08-13 |
| 478 | Improving Stylized Neural Machine Translation with Iterative Dual Knowledge Transfer Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose an iterative dual knowledge transfer framework that utilizes informal training data of machine translation and formality style transfer data to create large-scale stylized paired data, for the training of stylized machine translation model. |
XUANXUAN WU et. al. | ijcai | 2021-08-13 |
| 479 | Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Recently, an approximation to minimum Bayes risk (MBR) decoding has been proposed as an alternative decision rule that would likely not suffer from the same problems. We analyse this approximation and establish that it has no equivalent to the beam search curse. |
Bryan Eikema; Wilker Aziz; | arxiv-cs.CL | 2021-08-10 |
| 480 | The HW-TSC’s Offline Speech Translation Systems for IWSLT 2021 Evaluation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes our work in participation of the IWSLT-2021 offline speech translation task. |
MINGHAN WANG et. al. | arxiv-cs.CL | 2021-08-09 |
| 481 | Improving Similar Language Translation With Transfer Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work is part of our contribution to the WMT 2021 Similar Languages Translation Shared Task where we submitted models for different language pairs, including French-Bambara, Spanish-Catalan, and Spanish-Portuguese in both directions. |
Ife Adebara; Muhammad Abdul-Mageed; | arxiv-cs.AI | 2021-08-07 |
| 482 | Facebook AI WMT21 News Translation Task Submission Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe Facebook’s multilingual model submission to the WMT2021 shared task on news translation. |
CHAU TRAN et. al. | arxiv-cs.CL | 2021-08-06 |
| 483 | WeChat Neural Machine Translation Systems for WMT21 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces WeChat AI’s participation in WMT 2021 shared news translation task on English->Chinese, English->Japanese, Japanese->English and English->German. |
XIANFENG ZENG et. al. | arxiv-cs.CL | 2021-08-05 |
| 484 | ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We introduce ChrEnTranslate, an online machine translation demonstration system for translation between English and an endangered language Cherokee. |
Shiyue Zhang; Benjamin Frey; Mohit Bansal; | arxiv-cs.CL | 2021-07-30 |
| 485 | Difficulty-Aware Machine Translation Evaluation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a novel difficulty-aware MT evaluation metric, expanding the evaluation dimension by taking translation difficulty into consideration. |
Runzhe Zhan; Xuebo Liu; Derek F. Wong; Lidia S. Chao; | arxiv-cs.CL | 2021-07-29 |
| 486 | The Cross-Lingual Arabic Information REtrieval (CLAIRE) System Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we build our end-to-end Cross-Lingual Arabic Information REtrieval (CLAIRE) system based on the cross-lingual word embedding where searchers are assumed to have a passable passive understanding of Arabic and various supporting information in English is provided to aid retrieval experience. |
Zhizhong Chen; Carsten Eickhoff; | arxiv-cs.IR | 2021-07-29 |
| 487 | Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose sequence-level knowledge distillation (SKD) using perturbed length-aware positional encoding and apply it to a student model, the Levenshtein Transformer. |
Yui Oka; Katsuhito Sudoh; Satoshi Nakamura; | arxiv-cs.CL | 2021-07-28 |
| 488 | Cross-lingual Transferring of Pre-trained Contextualized Language Models Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, building upon the recent works connecting cross-lingual model transferring and neural machine translation, we thus propose a novel cross-lingual model transferring framework for PrLMs: TreLM. |
ZUCHAO LI et. al. | arxiv-cs.CL | 2021-07-27 |
| 489 | Do Context-Aware Translation Models Pay The Right Attention? Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To answer these questions, we introduce SCAT (Supporting Context for Ambiguous Translations), a new English-French dataset comprising supporting context words for 14K translations that professional translators found useful for pronoun disambiguation. |
KAYO YIN et. al. | acl | 2021-07-26 |
| 490 | XLPT-AMR: Cross-Lingual Pre-Training Via Multi-Task Learning for Zero-Shot AMR Parsing and Text Generation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Upon the availability of English AMR dataset and English-to- X parallel datasets, in this paper we propose a novel cross-lingual pre-training approach via multi-task learning (MTL) for both zeroshot AMR parsing and AMR-to-text generation. |
Dongqin Xu; Junhui Li; Muhua Zhu; Min Zhang; Guodong Zhou; | acl | 2021-07-26 |
| 491 | Lightweight Adapter Tuning for Multilingual Speech Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: While adapter tuning was investigated for multilingual neural machine translation, this paper proposes a comprehensive analysis of adapters for multilingual speech translation (ST). |
HANG LE et. al. | acl | 2021-07-26 |
| 492 | Improving Speech Translation By Understanding and Learning from The Auxiliary Text Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we are interested in training a speech translation model along with an auxiliary text translation task. |
Yun Tang; Juan Pino; Xian Li; Changhan Wang; Dmitriy Genzel; | acl | 2021-07-26 |
| 493 | Beyond Noise: Mitigating The Impact of Fine-grained Semantic Divergences on Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Based on these findings, we introduce a divergent-aware NMT framework that uses factors to help NMT recover from the degradation caused by naturally occurring divergences, improving both translation quality and model calibration on EN-FR tasks. |
Eleftheria Briakou; Marine Carpuat; | acl | 2021-07-26 |
| 494 | On Compositional Generalization of Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we study NMT models from the perspective of compositional generalization by building a benchmark dataset, CoGnition, consisting of 216k clean and consistent sentence pairs. |
Yafu Li; Yongjing Yin; Yulong Chen; Yue Zhang; | acl | 2021-07-26 |
| 495 | Improving Zero-Shot Translation By Disentangling Positional Information IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We demonstrate that a main factor causing the language-specific representations is the positional correspondence to input tokens. We show that this can be easily alleviated by removing residual connections in an encoder layer. |
Danni Liu; Jan Niehues; James Cross; Francisco Guzm?n; Xian Li; | acl | 2021-07-26 |
| 496 | Multilingual Agreement for Multilingual Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel agreement-based method to encourage multilingual agreement among different translation directions, which minimizes the differences among them. |
JIAN YANG et. al. | acl | 2021-07-26 |
| 497 | Towards User-Driven Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To fill this gap, we introduce a novel framework called user-driven NMT. |
HUAN LIN et. al. | acl | 2021-07-26 |
| 498 | Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate architectures and techniques commonly used to speed up decoding in Transformer-based models, such as greedy search, quantization, average attention networks (AANs) and shallow decoder models and show their effect on gendered noun translation. |
Adithya Renduchintala; Denise Diaz; Kenneth Heafield; Xian Li; Mona Diab; | acl | 2021-07-26 |
| 499 | Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a sophisticated neural architecture to incorporate bilingual dictionaries into Neural Machine Translation (NMT) models. |
TONG ZHANG et. al. | acl | 2021-07-26 |
| 500 | Online Learning Meets Machine Translation Evaluation: Finding The Best Systems with The Least Human Effort Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To overcome the latter challenge, we propose a novel application of online learning that, given an ensemble of Machine Translation systems, dynamically converges to the best systems, by taking advantage of the human feedback available. |
V?nia Mendon?a; Ricardo Rei; Luisa Coheur; Alberto Sardinha; Ana L?cia Santos; | acl | 2021-07-26 |
| 501 | Breaking The Corpus Bottleneck for Context-Aware Neural Machine Translation with Cross-Task Pre-training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To break the corpus bottleneck, in this paper we aim to improve context-aware NMT by taking the advantage of the availability of both large-scale sentence-level parallel dataset and source-side monolingual documents. |
LINQING CHEN et. al. | acl | 2021-07-26 |
| 502 | Beyond Sentence-Level End-to-End Speech Translation: Context Helps Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We investigate several decoding approaches, and introduce in-model ensemble decoding which jointly performs document- and sentence-level translation using the same model. |
Biao Zhang; Ivan Titov; Barry Haddow; Rico Sennrich; | acl | 2021-07-26 |
| 503 | Revisiting Negation in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we evaluate the translation of negation both automatically and manually, in English–German (EN–DE) and English–Chinese (EN–ZH). |
Gongbo Tang; Philipp Rönchen; Rico Sennrich; Joakim Nivre; | arxiv-cs.CL | 2021-07-26 |
| 504 | Selective Knowledge Distillation for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we design a novel protocol that can effectively analyze the different impacts of samples by comparing various samples’ partitions. |
Fusheng Wang; Jianhao Yan; Fandong Meng; Jie Zhou; | acl | 2021-07-26 |
| 505 | Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose a novel bilingual mutual information (BMI) based adaptive objective, which measures the learning difficulty for each target token from the perspective of bilingualism, and assigns an adaptive weight accordingly to improve token-level adaptive training. |
YANGYIFAN XU et. al. | acl | 2021-07-26 |
| 506 | Diverse Pretrained Context Encodings Improve Document Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pre-trained document context signals and assess the impact on translation performance of (1) different pretraining approaches for generating these signals, (2) the quantity of parallel data for which document context is available, and (3) conditioning on source, target, or source and target contexts. |
Domenic Donato; Lei Yu; Chris Dyer; | acl | 2021-07-26 |
| 507 | Lexicon Learning for Few Shot Sequence Modeling IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To address this, we augment neural decoders with a lexical translation mechanism that generalizes existing copy mechanisms to incorporate learned, decontextualized, token-level translation rules. |
Ekin Akyurek; Jacob Andreas; | acl | 2021-07-26 |
| 508 | Don’t Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we present a data collection strategy for MT which, in contrast, is cheap and simple, as it does not require bilingual speakers. |
Rajat Bhatnagar; Ananya Ganesh; Katharina Kann; | acl | 2021-07-26 |
| 509 | Learning Language Specific Sub-network for Multilingual Machine Translation IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose LaSS to jointly train a single unified multilingual MT model. |
Zehui Lin; Liwei Wu; Mingxuan Wang; Lei Li; | acl | 2021-07-26 |
| 510 | CCMatrix: Mining Billions of High-Quality Parallel Sentences on The Web IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We show that margin-based bitext mining in a multilingual sentence space can be successfully scaled to operate on monolingual corpora of billions of sentences. |
HOLGER SCHWENK et. al. | acl | 2021-07-26 |
| 511 | Good for Misconceived Reasons: An Empirical Revisiting on The Need for Visual Context in Multimodal Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Upon further investigation, we discover that the improvements achieved by the multimodal models over text-only counterparts are in fact results of the regularization effect. |
Zhiyong Wu; Lingpeng Kong; Wei Bi; Xiang Li; Ben Kao; | acl | 2021-07-26 |
| 512 | Crafting Adversarial Examples for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate veritable evaluations of NMT adversarial attacks, and propose a novel method to craft NMT adversarial examples. |
Xinze Zhang; Junzhe Zhang; Zhenhua Chen; Kun He; | acl | 2021-07-26 |
| 513 | Contrastive Learning for Many-to-many Multilingual Neural Machine Translation IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we aim to build a many-to-many translation system with an emphasis on the quality of non-English language directions. |
Xiao Pan; Mingxuan Wang; Liwei Wu; Lei Li; | acl | 2021-07-26 |
| 514 | G-Transformer for Document-Level Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: As a solution, we propose G-Transformer, introducing locality assumption as an inductive bias into Transformer, reducing the hypothesis space of the attention from target to source. |
Guangsheng Bao; Yue Zhang; Zhiyang Teng; Boxing Chen; Weihua Luo; | acl | 2021-07-26 |
| 515 | Consistency Regularization for Cross-Lingual Fine-Tuning Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. |
BO ZHENG et. al. | acl | 2021-07-26 |
| 516 | Cross-language Sentence Selection Via Data Augmentation and Rationale Training Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes an approach to cross-language sentence selection in a low-resource setting. |
YANDA CHEN et. al. | acl | 2021-07-26 |
| 517 | Adapting High-resource NMT Models to Translate Low-resource Related Languages Without Parallel Data Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we exploit this linguistic overlap to facilitate translating to and from a low-resource language with only monolingual data, in addition to any parallel data in the related high-resource language. |
WEI-JEN KO et. al. | acl | 2021-07-26 |
| 518 | Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we propose to improve the sampling procedure by selecting the most informative monolingual sentences to complement the parallel data. |
WENXIANG JIAO et. al. | acl | 2021-07-26 |
| 519 | From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we adapt a state-of-the-art neural machine translation model to generate Hindi-English code-switched sentences starting from monolingual Hindi sentences. |
Ishan Tarunesh; Syamantak Kumar; Preethi Jyothi; | acl | 2021-07-26 |
| 520 | End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we focus on methods based on training the model with constraints provided as part of the input sequence. |
Josef Jon; Jo?o Paulo Aires; Dusan Varis; Ondrej Bojar; | acl | 2021-07-26 |
| 521 | Fast and Accurate Neural Machine Translation with Translation Memory Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a fast and accurate approach to TM-based NMT within the Transformer framework: the model architecture is simple and employs a single bilingual sentence as its TM, leading to efficient training and inference; and its parameters are effectively optimized through a novel training criterion. |
Qiuxiang He; Guoping Huang; Qu Cui; Li Li; Lemao Liu; | acl | 2021-07-26 |
| 522 | Rewriter-Evaluator Architecture for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we introduce a novel architecture of Rewriter-Evaluator. |
Yangming Li; Kaisheng Yao; | acl | 2021-07-26 |
| 523 | Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we introduce another decoder, called seer decoder, into the encoder-decoder framework during training, which involves future information in target predictions. |
Yang Feng; Shuhao Gu; Dengji Guo; Zhengxin Yang; Chenze Shao; | acl | 2021-07-26 |
| 524 | Glancing Transformer for Non-Autoregressive Neural Machine Translation IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the Glancing Language Model (GLM) for single-pass parallel generation models. |
LIHUA QIAN et. al. | acl | 2021-07-26 |
| 525 | Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to efficiently increase the capacity for multilingual NMT by increasing the cardinality. |
Hongfei Xu; Qiuhui Liu; Josef van Genabith; Deyi Xiong; | acl | 2021-07-26 |
| 526 | Unsupervised Neural Machine Translation for Low-Resource Domains Via Meta-Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, this paper presents a novel meta-learning algorithm for unsupervised neural machine translation (UNMT) that trains the model to adapt to another domain by utilizing only a small amount of training data. |
CHEONBOK PARK et. al. | acl | 2021-07-26 |
| 527 | BERTGen: Multi-task Generation Through BERT Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present BERTGen, a novel, generative, decoder-only model which extends BERT by fusing multimodal and multilingual pre-trained models VL-BERT and M-BERT, respectively. |
Faidon Mitzalis; Ozan Caglayan; Pranava Madhyastha; Lucia Specia; | acl | 2021-07-26 |
| 528 | Neural Machine Translation with Monolingual Translation Memory IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In contrast to existing work that uses bilingual corpus as TM and employs source-side similarity search for memory retrieval, we propose a new framework that uses monolingual memory and performs learnable memory retrieval in a cross-lingual manner. |
Deng Cai; Yan Wang; Huayang Li; Wai Lam; Lemao Liu; | acl | 2021-07-26 |
| 529 | Mid-Air Hand Gestures for Post-Editing of Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Here, we present the first study that investigates the usefulness of mid-air hand gestures in combination with the keyboard (GK) for text editing in PE of MT. Guided by a gesture elicitation study with 14 freelance translators, we develop a prototype supporting mid-air hand gestures for cursor placement, text selection, deletion, and reordering. |
Rashad Albo Jamara; Nico Herbig; Antonio Kr?ger; Josef van Genabith; | acl | 2021-07-26 |
| 530 | Adaptive Nearest Neighbor Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose Adaptive kNN-MT to dynamically determine the number of k for each target token. |
XIN ZHENG et. al. | acl | 2021-07-26 |
| 531 | Modeling Bilingual Conversational Characteristics for Neural Chat Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we aim to promote the translation quality of conversational text by modeling the above properties. |
Yunlong Liang; Fandong Meng; Yufeng Chen; Jinan Xu; Jie Zhou; | acl | 2021-07-26 |
| 532 | Measuring and Increasing Context Usage in Context-Aware Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we introduce a new metric, conditional cross-mutual information, to quantify usage of context by these models. |
Patrick Fernandes; Kayo Yin; Graham Neubig; Andr? F. T. Martins; | acl | 2021-07-26 |
| 533 | Importance-based Neuron Allocation for Multilingual Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To solve these problems, we propose to divide the model neurons into general and language-specific parts based on their importance across languages. |
Wanying Xie; Yang Feng; Shuhao Gu; Dong Yu; | acl | 2021-07-26 |
| 534 | Prevent The Language Model from Being Overconfident in Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Based on the property, we propose a Margin-based Token-level Objective (MTO) and a Margin-based Sentence-level Objective (MSO) to maximize the Margin for preventing the LM from being overconfident. |
Mengqi Miao; Fandong Meng; Yijin Liu; Xiao-Hua Zhou; Jie Zhou; | acl | 2021-07-26 |
| 535 | The USYD-JD Speech Translation System for IWSLT 2021 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes the University of Sydney& JD’s joint submission of the IWSLT 2021 low resource speech translation task. |
Liang Ding; Di Wu; Dacheng Tao; | arxiv-cs.CL | 2021-07-24 |
| 536 | Extending Challenge Sets to Uncover Gender Bias in Machine Translation: Impact of Stereotypical Verbs and Adjectives Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present an extension of this challenge set, called WiBeMT, with gender-biased adjectives and adds sentences with gender-biased verbs. |
Jonas-Dario Troles; Ute Schmid; | arxiv-cs.CL | 2021-07-24 |
| 537 | MDQE: A More Accurate Direct Pretraining for Machine Translation Quality Estimation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on previous related work that have alleviated gaps to some extent, we propose a novel framework that provides a more accurate direct pretraining for QE tasks. |
Lei Lin; | arxiv-cs.CL | 2021-07-24 |
| 538 | Modelling Latent Translations for Cross-Lingual Transfer Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To remedy this, we propose a new technique that integrates both steps of the traditional pipeline (translation and classification) into a single model, by treating the intermediate translations as a latent random variable. |
Edoardo Maria Ponti; Julia Kreutzer; Ivan Vulić; Siva Reddy; | arxiv-cs.CL | 2021-07-23 |
| 539 | Confidence-Aware Scheduled Sampling for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To address this issue, we propose confidence-aware scheduled sampling. |
Yijin Liu; Fandong Meng; Yufeng Chen; Jinan Xu; Jie Zhou; | arxiv-cs.CL | 2021-07-21 |
| 540 | Integrating Unsupervised Data Generation Into Self-Supervised Neural Machine Translation for Low-Resource Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, unsupervised machine translation (UMT) exploits large amounts of monolingual data by using synthetic data generation techniques such as back-translation and noising, while self-supervised NMT (SSNMT) identifies parallel sentences in smaller comparable data and trains on them. |
Dana Ruiter; Dietrich Klakow; Josef van Genabith; Cristina España-Bonet; | arxiv-cs.CL | 2021-07-19 |
| 541 | As Easy As 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work we develop comprehensive assessments of the robustness of neural machine translation systems to numerical text via behavioural testing. |
JUN WANG et. al. | arxiv-cs.CL | 2021-07-18 |
| 542 | Picard Understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in A Constructed Language Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: Tamarian, a fictional language introduced in the Star Trek episode Darmok, communicates meaning through utterances of metaphorical references, such as Darmok and Jalad at Tanagra instead of We should work together. This work assembles a Tamarian-English dictionary of utterances from the original episode and several follow-on novels, and uses this to construct a parallel corpus of 456 English-Tamarian utterances. |
Peter Jansen; Jordan Boyd-Graber; | arxiv-cs.CL | 2021-07-16 |
| 543 | FST: The FAIR Speech Translation System for The IWSLT21 Multilingual Shared Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. |
YUN TANG et. al. | arxiv-cs.CL | 2021-07-14 |
| 544 | Zero-shot Speech Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: These models tend to output the wrong language when performing zero-shot ST. We tackle the issues by including additional training data and an auxiliary loss function that minimizes the text-audio difference. |
Tu Anh Dinh; | arxiv-cs.CL | 2021-07-13 |
| 545 | The IWSLT 2021 BUT Speech Translation Systems Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study their efficiency from the perspective of having a large amount of separate ASR training data and MT training data, and a smaller amount of speech-translation training data. |
Hari Krishna Vydana; Martin Karafi’at; Luk’as Burget; Honza Cernock’y; | arxiv-cs.CL | 2021-07-13 |
| 546 | Putting Words Into The System’s Mouth: A Targeted Attack on Neural Machine Translation Using Monolingual Data Poisoning Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We present two methods for crafting poisoned examples, and show that only a tiny handful of instances, amounting to only 0.02% of the training set, is sufficient to enact a successful attack. |
JUN WANG et. al. | arxiv-cs.CL | 2021-07-12 |
| 547 | Using Machine Translation to Localize Task Oriented NLG Output Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper explores doing this by applying machine translation to the English output. |
SCOTT ROY et. al. | arxiv-cs.CL | 2021-07-09 |
| 548 | Mixed Cross Entropy Loss for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this paper, we propose mixed Cross Entropy loss (mixed CE) as a substitute for CE in both training approaches. |
Haoran Li; Wei Lu; | icml | 2021-07-08 |
| 549 | Temporally Correlated Task Scheduling for Sequence Learning Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we introduce a learnable scheduler to sequence learning, which can adaptively select auxiliary tasks for training depending on the model status and the current training data. |
XUEQING WU et. al. | icml | 2021-07-08 |
| 550 | Using CollGram to Compare Formulaic Language in Human and Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Abstract: A comparison of formulaic sequences in human and neural machine translation of quality newspaper articles shows that neural machine translations contain less lower-frequency, but … |
Yves Bestgen; | arxiv-cs.CL | 2021-07-08 |
| 551 | Self-supervised and Supervised Joint Training for Resource-rich Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a joint training approach, F2-XEnDec, to combine self-supervised and supervised learning to optimize NMT models. |
Yong Cheng; Wei Wang; Lu Jiang; Wolfgang Macherey; | icml | 2021-07-08 |
| 552 | Cross-model Back-translated Distillation for Unsupervised Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: We introduce a novel component to the standard UMT framework called Cross-model Back-translated Distillation (CBD), that is aimed to induce another level of data diversification that existing principles lack. |
Xuan-Phi Nguyen; Shafiq Joty; Thanh-Tung Nguyen; Kui Wu; Ai Ti Aw; | icml | 2021-07-08 |
| 553 | A Topic Guided Pointer-Generator Model for Generating Natural Language Code Summaries Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a neural network model named ToPNN for code summarization, which uses the topics in a broader context (e.g., class) to guide the neural networks that combine the generation of new words and the copy of existing words in code. |
XIN WANG et. al. | arxiv-cs.SE | 2021-07-04 |
| 554 | IITP at WAT 2021: System Description for English-Hindi Multimodal Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We participate in the 8th Workshop on Asian Translation (WAT – 2021) for English-Hindi multimodal translation task and achieve 42.47 and 37.50 BLEU points for Evaluation and Challenge subset, respectively. |
Baban Gain; Dibyanayan Bandyopadhyay; Asif Ekbal; | arxiv-cs.CL | 2021-07-04 |
| 555 | Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the benefit that such compositionality brings about to several machine translation tasks. |
Rahma Chaabouni; Roberto Dessì; Eugene Kharitonov; | arxiv-cs.CL | 2021-07-03 |
| 556 | Zero-pronoun Data Augmentation for Japanese-to-English Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose a data augmentation method that provides additional training signals for the translation model to learn correlations between local context and zero pronouns. |
Ryokan Ri; Toshiaki Nakazawa; Yoshimasa Tsuruoka; | arxiv-cs.CL | 2021-07-01 |
| 557 | Modeling Target-side Inflection in Placeholder Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To address this problem, we propose a novel method of placeholder translation that can inflect specified terms according to the grammatical construction of the output sentence. |
Ryokan Ri; Toshiaki Nakazawa; Yoshimasa Tsuruoka; | arxiv-cs.CL | 2021-07-01 |
| 558 | The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes USTC-NELSLIP’s submissions to the IWSLT2021 Simultaneous Speech Translation task. |
Dan Liu; Mengge Du; Xiaoxi Li; Yuchen Hu; Lirong Dai; | arxiv-cs.CL | 2021-07-01 |
| 559 | IMS’ Systems for The IWSLT 2021 Low-Resource Speech Translation Task Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes the submission to the IWSLT 2021 Low-Resource Speech Translation Shared Task by IMS team. |
Pavel Denisov; Manuel Mager; Ngoc Thang Vu; | arxiv-cs.CL | 2021-06-30 |
| 560 | DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation By Augmenting Pretrained Multilingual Encoders IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To reduce this gap, we introduce DeltaLM, a pretrained multilingual encoder-decoder model that regards the decoder as the task layer of off-the-shelf pretrained encoders. |
SHUMING MA et. al. | arxiv-cs.CL | 2021-06-25 |
| 561 | Language Models Are Good Translators Literature Review Related Patents Related Grants Related Orgs Related Experts Details Abstract: Recent years have witnessed the rapid advance in neural machine translation (NMT), the core of which lies in the encoder-decoder architecture. Inspired by the recent progress of … |
SHUO WANG et. al. | arxiv-cs.CL | 2021-06-25 |
| 562 | On The Influence of Machine Translation on Language Origin Obfuscation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we analyze the ability to detect the source language from the translated output of two widely used commercial machine translation systems by utilizing machine-learning algorithms with basic textual features like n-grams. |
Benjamin Murauer; Michael Tschuggnall; Günther Specht; | arxiv-cs.CL | 2021-06-24 |
| 563 | End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we focus on methods based on training the model with constraints provided as part of the input sequence. |
Josef Jon; João Paulo Aires; Dušan Variš; Ondřej Bojar; | arxiv-cs.CL | 2021-06-23 |
| 564 | Dealing with Training and Test Segmentation Mismatch: FBK@IWSLT2021 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes FBK’s system submission to the IWSLT 2021 Offline Speech Translation task. |
Sara Papi; Marco Gaido; Matteo Negri; Marco Turchi; | arxiv-cs.CL | 2021-06-23 |
| 565 | Phrase-level Active Learning for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this problem in an active learning setting where we can spend a given budget on translating in-domain data, and gradually fine-tune a pre-trained out-of-domain NMT model on the newly translated data. |
Junjie Hu; Graham Neubig; | arxiv-cs.CL | 2021-06-21 |
| 566 | Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to share parameters across all layers thereby leading to a recurrently stacked neural network model. |
Raj Dabre; Atsushi Fujita; | arxiv-cs.CL | 2021-06-18 |
| 567 | Lost in Interpreting: Speech Translation from Source or Interpreter? Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate if such an automatic system should rather follow the original speaker, or an interpreter to achieve better translation quality at the cost of increased delay. |
Dominik Macháček; Matúš Žilinec; Ondřej Bojar; | arxiv-cs.CL | 2021-06-17 |
| 568 | Central Kurdish Machine Translation: First Large Scale Parallel Corpus and Experiments Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present the first large scale parallel corpus of Central Kurdish-English, Awta, containing 229,222 pairs of manually aligned translations. |
Zhila Amini; Mohammad Mohammadamini; Hawre Hosseini; Mehran Mansouri; Daban Jaff; | arxiv-cs.AI | 2021-06-17 |
| 569 | Evaluating Gender Bias in Hindi-English Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We implement a modified version of the existing TGBI metric based on the grammatical considerations for Hindi. |
Gauri Gupta; Krithika Ramesh; Sanjay Singh; | arxiv-cs.CL | 2021-06-16 |
| 570 | Alternated Training with Synthetic and Authentic Data for Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose alternated training with synthetic and authentic data for NMT. Compared with previous work, we introduce authentic data as guidance to prevent the training of NMT models from being disturbed by noisy synthetic data. |
Rui Jiao; Zonghan Yang; Maosong Sun; Yang Liu; | arxiv-cs.CL | 2021-06-16 |
| 571 | Language Tags Matter for Zero-Shot Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we demonstrate that the LTs are not only indicators for translation directions but also crucial to zero-shot translation qualities. |
Liwei Wu; Shanbo Cheng; Mingxuan Wang; Lei Li; | arxiv-cs.CL | 2021-06-15 |
| 572 | Sequence-Level Training for Non-Autoregressive Neural Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this article, we propose using sequence-level training objectives to train NAT models, which evaluate the NAT outputs as a whole and correlates well with the real translation quality. |
Chenze Shao; Yang Feng; Jinchao Zhang; Fandong Meng; Jie Zhou; | arxiv-cs.CL | 2021-06-15 |
| 573 | English to Bangla Machine Translation Using Recurrent Neural Network Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes an architecture of English to Bangla machine translation system. |
Shaykh Siddique; Tahmid Ahmed; Md. Rifayet Azam Talukder; Md. Mohsin Uddin; | arxiv-cs.CL | 2021-06-14 |
| 574 | Machine Translation Into Low-resource Language Varieties Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a general framework to rapidly adapt MT systems to generate language varieties that are close to, but different from, the standard target language, using no parallel (source–variety) data. |
Sachin Kumar; Antonios Anastasopoulos; Shuly Wintner; Yulia Tsvetkov; | arxiv-cs.CL | 2021-06-12 |
| 575 | UC2: Universal Cross-Lingual Cross-Modal Vision-and-Language Pre-Training IF:3 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: To generalize this success to non-English languages, we introduce UC^2, the first machine translation-augmented framework for cross-lingual cross-modal representation learning. |
MINGYANG ZHOU et. al. | cvpr | 2021-06-11 |
| 576 | Exploring Unsupervised Pretraining Objectives for Machine Translation Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: In this work, we systematically compare masking with alternative objectives that produce inputs resembling real (full) sentences, by reordering and replacing words based on their context. |
Christos Baziotis; Ivan Titov; Alexandra Birch; Barry Haddow; | arxiv-cs.CL | 2021-06-10 |
| 577 | Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021 Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes our systems that were submitted to the restricted translation task at WAT 2021. |
Katsuki Chousa; Makoto Morishita; | arxiv-cs.CL | 2021-06-09 |
| 578 | Crosslingual Embeddings Are Essential in UNMT for Distant Languages: An English to IndoAryan Case Study Literature Review Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that initializing the embedding layer of UNMT models with cross-lingual embeddings shows significant improvements in BLEU score over existing approaches with embeddings randomly initialized. |
Tamali Banerjee; Rudra Murthy V; Pushpak Bhattacharyya; | arxiv-cs.CL | 2021-06-09 |
| 579 | Multilingual Neural Semantic Parsing for Low-Resourced Languages Literature Review Related Patents Related Grants Related Orgs Related Experts Related Code Details Highlight: To tackle the data limitation problem, we propose using machine translation to bootstrap multilingual training data from the more abundant English data. To evaluate our multilingual models on human-written sentences as opposed to machine translated ones, we introduce a new multilingual semantic parsing dataset in English, Italian and Japanese based on the Facebook Task Oriented Parsing (TOP) dataset. |
Menglin Xia; Emilio Monti; | arxiv-cs.CL | 2021-06-07 |
| 580 | Lexicon Learning |