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.
If you do not want to miss any interesting academic paper, 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
team@paperdigest.org
TABLE 1: Paper Digest: Recent Papers on Machine Translation
| Title | Author(s) | Highlight | Category | Date | |
|---|---|---|---|---|---|
| 1 | Exploiting Neural Query Translation Into Cross Lingual Information Retrieval | LIANG YAO et. al. | In this paper, we investigate how to exploit neural query translation model into CLIR system. | CS.arxiv | 2020-10-26 |
| 2 | Constraint Translation Candidates: A Bridge Between Neural Query Translation And Cross-lingual Information Retrieval | TIANCHI BI et. al. | In this paper, we propose a novel approach to alleviate these problems by limiting the open target vocabulary search space of QT to a set of important words mined from search index database. | CS.arxiv | 2020-10-26 |
| 3 | Is It Great Or Terrible? Preserving Sentiment In Neural Machine Translation Of Arabic Reviews | HADEEL SAADANY et. al. | In this paper we investigate the challenges involved in translating book reviews from Arabic into English, with particular focus on the errors that lead to incorrect translation of sentiment polarity. | CS.arxiv | 2020-10-26 |
| 4 | Data Troubles In Sentence Level Confidence Estimation For Machine Translation | CIPRIAN CHELBA et. al. | As a side product of the data annotation process necessary for building such models we propose sentence level accuracy $SACC$ as a simple, self-explanatory evaluation metric for quality of translation. | CS.arxiv | 2020-10-26 |
| 5 | Curious Case Of Language Generation Evaluation Metrics: A Cautionary Tale | OZAN CAGLAYAN et. al. | In this paper, we urge the community for more careful consideration of how they automatically evaluate their models by demonstrating important failure cases on multiple datasets, language pairs and tasks. | CS.arxiv | 2020-10-26 |
| 6 | ReadOnce Transformers: Reusable Representations Of Text For Transformers | SHIH-TING LIN et. al. | We present a transformer-based approach, ReadOnce Transformers, that is trained to build such information-capturing representations of text. | CS.arxiv | 2020-10-24 |
| 8 | Context-aware Decoder For Neural Machine Translation Using A Target-side Document-Level Language Model | AMANE SUGIYAMA et. al. | We therefore present a simple method to turn a sentence-level translation model into a context-aware model by incorporating a document-level language model into the decoder. | CS.arxiv | 2020-10-24 |
| 10 | On Learning Text Style Transfer With Direct Rewards | YIXIN LIU et. al. | In this paper, we explore training algorithms that instead optimize reward functions that explicitly consider different aspects of the style-transferred outputs. | CS.arxiv | 2020-10-24 |
| 11 | Customizing Triggers With Concealed Data Poisoning | ERIC WALLACE et. al. | In this work, we develop a new data poisoning attack that allows an adversary to control model predictions whenever a desired trigger phrase is present in the input. | CS.arxiv | 2020-10-23 |
| 12 | Rapid Domain Adaptation For Machine Translation With Monolingual Data | MAHDIS MAHDIEH et. al. | In this paper, we propose an approach that enables rapid domain adaptation from the perspective of unsupervised translation. | CS.arxiv | 2020-10-23 |
| 13 | Anchor-based Bilingual Word Embeddings For Low-Resource Languages | TOBIAS EDER et. al. | This paper proposes a new approach for building BWEs in which the vector space of the high resource source language is used as a starting point for training an embedding space for the low resource target language. | CS.arxiv | 2020-10-23 |
| 14 | CUNI Systems For The Unsupervised And Very Low Resource Translation Task In WMT20 | IVANA KVAPILÍKOVÁ et. al. | This paper presents a description of CUNI systems submitted to the WMT20 task on unsupervised and very low-resource supervised machine translation between German and Upper Sorbian. | CS.arxiv | 2020-10-22 |
| 15 | MT5: A Massively Multilingual Pre-trained Text-to-text Transformer | LINTING XUE et. al. | In this paper, we introduce mT5, a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering 101 languages. | CS.arxiv | 2020-10-22 |
| 16 | XOR QA: Cross-lingual Open-Retrieval Question Answering | AKARI ASAI et. al. | Based on this dataset, we introduce three new tasks that involve cross-lingual document retrieval using multi-lingual and English resources. We construct a large-scale dataset built on questions from TyDi QA lacking same-language answers. | CS.arxiv | 2020-10-22 |
| 17 | Not All Parameters Are Born Equal: Attention Is Mostly What You Need | NIKOLAY BOGOYCHEV | To gain insight into this, we consider three groups of parameters: embeddings, attention, and feed forward neural network (FFN) layers. | CS.arxiv | 2020-10-22 |
| 18 | Sentence Boundary Augmentation For Neural Machine Translation Robustness | DANIEL LI et. al. | Through in-depth error analysis, we show that sentence boundary segmentation has the largest impact on quality, and we develop a simple data augmentation strategy to improve segmentation robustness. | CS.arxiv | 2020-10-21 |
| 19 | Beyond English-Centric Multilingual Machine Translation | ANGELA FAN et. al. | In this work, we create a true Many-to-Many multilingual translation model that can translate directly between any pair of 100 languages. We build and open source a training dataset that covers thousands of language directions with supervised data, created through large-scale mining. | CS.arxiv | 2020-10-21 |
| 20 | A General Multi-Task Learning Framework To Leverage Text Data For Speech To Text Tasks | YUN TANG et. al. | In this study, we propose a general multi-task learning framework to leverage text data for ASR and ST tasks. | CS.arxiv | 2020-10-21 |
| 21 | Exploring Sequence-to-Sequence Models For SPARQL Pattern Composition | ANAND PANCHBHAI et. al. | In this short paper, we explore the use of architectures based on Neural Machine Translation called Neural SPARQL Machines to learn pattern compositions. | CS.arxiv | 2020-10-21 |
| 22 | Analyzing The Source And Target Contributions To Predictions In Neural Machine Translation | ELENA VOITA et. al. | We extend LRP to the Transformer and conduct an analysis of NMT models which explicitly evaluates the source and target relative contributions to the generation process. | CS.arxiv | 2020-10-21 |
| 23 | Cascaded Models With Cyclic Feedback For Direct Speech Translation | TSZ KIN LAM et. al. | We present a technique that allows cascades of automatic speech recognition (ASR) and machine translation (MT) to exploit in-domain direct speech translation data in addition to out-of-domain MT and ASR data. | CS.arxiv | 2020-10-21 |
| 24 | Token Drop Mechanism For Neural Machine Translation | HUAAO ZHANG et. al. | We propose Token Drop to improve generalization and avoid overfitting for the NMT model. | CS.arxiv | 2020-10-21 |
| 25 | TMT: A Transformer-based Modal Translator For Improving Multimodal Sequence Representations In Audio Visual Scene-aware Dialog | WUBO LI et. al. | Inspired by Neural Machine Translation (NMT), we propose the Transformer-based Modal Translator (TMT) to learn the representations of the source modal sequence by translating the source modal sequence to the related target modal sequence in a supervised manner. | CS.arxiv | 2020-10-21 |
| 26 | WaveTransformer: A Novel Architecture For Audio Captioning Based On Learning Temporal And Time-Frequency Information | AN TRAN et. al. | In this work we present a novel AAC novel method, explicitly focused on the exploitation of the temporal and time-frequency patterns in audio. | CS.arxiv | 2020-10-21 |
| 27 | On The Potential Of Lexico-logical Alignments For Semantic Parsing To SQL Queries | TIANZE SHI et. al. | We propose and test two methods: (1) supervised attention; (2) adopting an auxiliary objective of disambiguating references in the input queries to table columns. | CS.arxiv | 2020-10-21 |
| 28 | Human-Paraphrased References Improve Neural Machine Translation | MARKUS FREITAG et. al. | In this paper we compare the results of performing end-to-end system development using standard and paraphrased references. | CS.arxiv | 2020-10-20 |
| 29 | Complete Multilingual Neural Machine Translation | MARKUS FREITAG et. al. | Multilingual Neural Machine Translation (MNMT) models are commonly trained on a joint set of bilingual corpora which is acutely English-centric (i.e. English either as the source or target language). | CS.arxiv | 2020-10-20 |
| 30 | Word Shape Matters: Robust Machine Translation With Visual Embedding | HAOHAN WANG et. al. | Neural machine translation has achieved remarkable empirical performance over standard benchmark datasets, yet recent evidence suggests that the models can still fail easily dealing with substandard inputs such as misspelled words, To overcome this issue, we introduce a new encoding heuristic of the input symbols for character-level NLP models: it encodes the shape of each character through the images depicting the letters when printed. | CS.arxiv | 2020-10-20 |
| 31 | Pushing The Limits Of AMR Parsing With Self-Learning | YOUNG-SUK LEE et. al. | In this paper, we explore different ways in which trained models can be applied to improve AMR parsing performance, including generation of synthetic text and AMR annotations as well as refinement of actions oracle. | CS.arxiv | 2020-10-20 |
| 32 | Towards End-to-End In-Image Neural Machine Translation | ELMAN MANSIMOV et. al. | In this paper, we offer a preliminary investigation into the task of in-image machine translation: transforming an image containing text in one language into an image containing the same text in another language. | CS.arxiv | 2020-10-20 |
| 33 | Multi-Unit Transformers For Neural Machine Translation | JIANHAO YAN et. al. | In this paper, we propose the Multi-Unit Transformers (MUTE), which aim to promote the expressiveness of the Transformer by introducing diverse and complementary units. | CS.arxiv | 2020-10-20 |
| 34 | Unsupervised Pretraining For Neural Machine Translation Using Elastic Weight Consolidation | DUŠAN VARIŠ et. al. | This work presents our ongoing research of unsupervised pretraining in neural machine translation (NMT). | CS.arxiv | 2020-10-19 |
| 35 | Revisiting Modularized Multilingual NMT To Meet Industrial Demands | SUNGWON LYU et. al. | In this study, we revisit the multilingual neural machine translation model that only share modules among the same languages (M2) as a practical alternative to 1-1 to satisfy industrial requirements. | CS.arxiv | 2020-10-19 |
| 36 | Incorporating Terminology Constraints In Automatic Post-Editing | DAVID WAN et. al. | Incorporating Terminology Constraints In Automatic Post-Editing | CS.arxiv | 2020-10-19 |
| 37 | Diving Deep Into Context-Aware Neural Machine Translation | JINGJING HUO et. al. | This paper analyzes the performance of document-level NMT models on four diverse domains with a varied amount of parallel document-level bilingual data. | CS.arxiv | 2020-10-19 |
| 38 | Meta-Learning For Low-Resource Unsupervised Neural MachineTranslation | YUNWON TAE et. al. | To address this issue, this paper presents a 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. | CS.arxiv | 2020-10-18 |
| 39 | Capturing Longer Context For Document-level Neural Machine Translation: A Multi-resolutional Approach | ZEWEI SUN et. al. | In this paper, we propose multi-resolutional (MR) Doc2Doc, a method to train a neural sequence-to-sequence model for document-level translation. | CS.arxiv | 2020-10-18 |
| 40 | Incorporate Semantic Structures Into Machine Translation Evaluation Via UCCA | JIN XU et. al. | Therefore, in this work, we define words carrying important semantic meanings in sentences as semantic core words. | CS.arxiv | 2020-10-17 |
| 41 | A Corpus For English-Japanese Multimodal Neural Machine Translation With Comparable Sentences | ANDREW MERRITT et. al. | In this paper, we propose a new multimodal English-Japanese corpus with comparable sentences that are compiled from existing image captioning datasets. | CS.arxiv | 2020-10-17 |
| 42 | Training Flexible Depth Model By Multi-Task Learning For Neural Machine Translation | QIANG WANG et. al. | In this work, we propose to use multi-task learning to train a flexible depth model that can adapt to different depth configurations during inference. | CS.arxiv | 2020-10-16 |
| 43 | Generating Diverse Translation From Model Distribution With Dropout | XUANFU WU et. al. | In this paper, we propose to generate diverse translations by deriving a large number of possible models with Bayesian modelling and sampling models from them for inference. | CS.arxiv | 2020-10-16 |
| 44 | Multi-Task Learning For Cross-Lingual Abstractive Summarization | SHO TAKASE et. al. | We present a multi-task learning framework for cross-lingual abstractive summarization to augment training data. Recent studies constructed pseudo cross-lingual abstractive summarization data to train their neural encoder-decoders. Meanwhile, we introduce existing genuine data such as translation pairs and monolingual abstractive summarization data into training. | CS.arxiv | 2020-10-15 |
| 47 | Unsupervised Bitext Mining And Translation Via Self-trained Contextual Embeddings | PHILLIP KEUNG et. al. | We describe an unsupervised method to create pseudo-parallel corpora for machine translation (MT) from unaligned text. | CS.arxiv | 2020-10-15 |
| 48 | Dissecting The Components And Factors Of Neural Text Generation | KHYATHI RAGHAVI CHANDU et. al. | Specifically, this paper surveys the fundamental factors and components relaying task agnostic impacts across various generation tasks such as storytelling, summarization, translation etc., In specific, we present an abstraction of the imperative techniques with respect to learning paradigms, pretraining, modeling approaches, decoding and the key challenges. | CS.arxiv | 2020-10-14 |
| 49 | Semantic Label Smoothing For Sequence To Sequence Problems | MICHAL LUKASIK et. al. | Unlike these works, in this paper, we propose a technique that smooths over \emph{well formed} relevant sequences that not only have sufficient n-gram overlap with the target sequence, but are also \emph{semantically similar}. | CS.arxiv | 2020-10-14 |
| 50 | Fine-grained Linguistic Evaluation For State-of-the-art Machine Translation | ELEFTHERIOS AVRAMIDIS et. al. | This paper describes a test suite submission providing detailed statistics of linguistic performance for the state-of-the-art German-English systems of the Fifth Conference of Machine Translation (WMT20). | CS.arxiv | 2020-10-13 |
| 51 | The Tatoeba Translation Challenge — Realistic Data Sets For Low Resource And Multilingual MT | JÖRG TIEDEMANN | This paper describes the development of a new benchmark for machine translation that provides training and test data for thousands of language pairs covering over 500 languages and tools for creating state-of-the-art translation models from that collection. | CS.arxiv | 2020-10-13 |
| 52 | Ensemble Distillation For Structured Prediction: Calibrated, Accurate, Fast—Choose Three | STEVEN REICH et. al. | In this paper, we study ensemble distillation as a general framework for producing well-calibrated structured prediction models while avoiding the prohibitive inference-time cost of ensembles. | CS.arxiv | 2020-10-13 |
| 53 | Mitigating Gender Bias In Machine Translation With Target Gender Annotations | ARTŪRS STAFANOVIČS et. al. | Therefore, in this work, we propose to decouple the task of acquiring the necessary information from the task of learning to translate correctly when such information is available. | CS.arxiv | 2020-10-13 |
| 54 | With Little Power Comes Great Responsibility | DALLAS CARD et. al. | For machine translation, we find that typical test sets of 2000 sentences have approximately 75% power to detect differences of 1 BLEU point. | CS.arxiv | 2020-10-13 |
| 55 | Multilingual Argument Mining: Datasets And Analysis | ORITH TOLEDO-RONEN et. al. | In this work, we explore the potential of transfer learning using the multilingual BERT model to address argument mining tasks in non-English languages, based on English datasets and the use of machine translation. Finally, to facilitate evaluation of transfer learning on argument mining tasks, we provide a human-generated dataset with more than 10k arguments in multiple languages, as well as machine translation of the English datasets. | CS.arxiv | 2020-10-13 |
| 56 | Gradient Vaccine: Investigating And Improving Multi-task Optimization In Massively Multilingual Models | ZIRUI WANG et. al. | In this paper, we attempt to peek into the black-box of multilingual optimization through the lens of loss function geometry. | CS.arxiv | 2020-10-12 |
| 57 | Gender Coreference And Bias Evaluation At WMT 2020 | TOM KOCMI et. al. | Our work presents the largest evidence for the phenomenon in more than 19 systems submitted to the WMT over four diverse target languages: Czech, German, Polish, and Russian. | CS.arxiv | 2020-10-12 |
| 58 | Dynamic Context-guided Capsule Network For Multimodal Machine Translation | HUAN LIN et. al. | To address the above issues, in this paper, we propose a novel Dynamic Context-guided Capsule Network (DCCN) for MMT. | CS.mm | 2020-10-12 |
| 59 | Retrieval Guided Unsupervised Multi-domain Image To Image Translation | RAUL GOMEZ et. al. | In this paper we propose the use of an image retrieval system to assist the image-to-image translation task. | CS.mm | 2020-10-12 |
| 60 | Collective Wisdom: Improving Low-resource Neural Machine Translation Using Adaptive Knowledge Distillation | FAHIMEH SALEH et. al. | In this paper, we tackle this problem using knowledge distillation, where we propose to distill the knowledge of ensemble of teacher models to a single student model. | CS.arxiv | 2020-10-12 |
| 61 | Towards Machine Translation For The Kurdish Language | SINA AHMADI et. al. | Therefore, in this paper, we are addressing the main issues in creating a machine translation system for the Kurdish language, with a focus on the Sorani dialect. | CS.arxiv | 2020-10-12 |
| 62 | Look It Up: Bilingual And Monolingual Dictionaries Improve Neural Machine Translation | XING JIE ZHONG et. al. | In this paper, we describe a new method for attaching dictionary definitions to rare words so that the network can learn the best way to use them. | CS.arxiv | 2020-10-12 |
| 63 | Improving Text Generation With Student-Forcing Optimal Transport | GUOYIN WANG et. al. | To reduce this gap between training and testing, we propose using optimal transport (OT) to match the sequences generated in these two modes. | CS.arxiv | 2020-10-12 |
| 64 | Controllable Paraphrasing And Translation With A Syntactic Exemplar | MINGDA CHEN et. al. | Despite only using bitext for training, and in near zero-shot conditions, our single proposed model can perform four tasks: controlled paraphrase generation in both languages and controlled machine translation in both language directions. To evaluate these tasks quantitatively, we create three novel evaluation datasets. | CS.arxiv | 2020-10-12 |
| 65 | Incorporating BERT Into Parallel Sequence Decoding With Adapters | JUNLIANG GUO et. al. | In this paper, we propose to address this problem by taking two different BERT models as the encoder and decoder respectively, and fine-tuning them by introducing simple and lightweight adapter modules, which are inserted between BERT layers and tuned on the task-specific dataset. | CS.arxiv | 2020-10-12 |
| 66 | Detecting Foodborne Illness Complaints In Multiple Languages Using English Annotations Only | ZIYI LIU et. al. | We demonstrate the benefits of our approach through extensive experiments with Yelp restaurant reviews in seven languages. | CS.arxiv | 2020-10-11 |
| 67 | Lexically Cohesive Neural Machine Translation With Copy Mechanism | VIPUL MISHRA et. al. | We employ a copy mechanism into a context-aware neural machine translation model to allow copying words from previous translation outputs. | CS.arxiv | 2020-10-11 |
| 68 | Addressing Exposure Bias With Document Minimum Risk Training: Cambridge At The WMT20 Biomedical Translation Task | DANIELLE SAUNDERS et. al. | This can result in poor behaviour during inference if the model learns to neglect the source sentence. | CS.arxiv | 2020-10-11 |
| 69 | Neural Machine Translation Doesn’t Translate Gender Coreference Right Unless You Make It | DANIELLE SAUNDERS et. al. | In this paper we propose schemes for incorporating explicit word-level gender inflection tags into NMT. | CS.arxiv | 2020-10-11 |
| 70 | Machine Translation Of Mathematical Text | ADITYA OHRI et. al. | We have trained a Transformer-based translator model, using OpenNMT, on a combined corpus containing a small proportion of domain-specific sentences. | CS.arxiv | 2020-10-11 |
| 71 | Automated Prediction Of Medieval Arabic Diacritics | KHALID ALNAJJAR et. al. | This study uses a character level neural machine translation approach trained on a long short-term memory-based bi-directional recurrent neural network architecture for diacritization of Medieval Arabic. | CS.arxiv | 2020-10-11 |
| 72 | It’s Not A Non-Issue: Negation As A Source Of Error In Machine Translation | MD MOSHARAF HOSSAIN et. al. | In this study we focus on negation, a universal, core property of human language that significantly affects the semantics of an utterance. | CS.arxiv | 2020-10-11 |
| 73 | Fairseq S2T: Fast Speech-to-Text Modeling With Fairseq | CHANGHAN WANG et. al. | We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation. | CS.arxiv | 2020-10-11 |
| 74 | On Long-Tailed Phenomena In Neural Machine Translation | VIKAS RAUNAK et. al. | In this work, we quantitatively characterize such long-tailed phenomena at two levels of abstraction, namely, token classification and sequence generation. | CS.arxiv | 2020-10-10 |
| 75 | SJTU-NICT’s Supervised And Unsupervised Neural Machine Translation Systems For The WMT20 News Translation Task | ZUCHAO LI et. al. | In this paper, we introduced our joint team SJTU-NICT ‘s participation in the WMT 2020 machine translation shared task. | CS.arxiv | 2020-10-10 |
| 76 | Localizing Open-Ontology QA Semantic Parsers In A Day Using Machine Translation | MEHRAD MORADSHAHI. GIOVANNI CAMPAGNA et. al. | We propose Semantic Parser Localizer (SPL), a toolkit that leverages Neural Machine Translation (NMT) systems to localize a semantic parser for a new language. | CS.arxiv | 2020-10-10 |
| 77 | Mark-Evaluate: Assessing Language Generation Using Population Estimation Methods | GONÇALO MORDIDO et. al. | We propose a family of metrics to assess language generation derived from population estimation methods widely used in ecology. | CS.arxiv | 2020-10-09 |
| 78 | ChrEn: Cherokee-English Machine Translation For Endangered Language Revitalization | SHIYUE ZHANG et. al. | To help save this endangered language, we introduce ChrEn, a Cherokee-English parallel dataset, to facilitate machine translation research between Cherokee and English. We also collect 5k Cherokee monolingual data to enable semi-supervised learning. | CS.arxiv | 2020-10-09 |
| 79 | Recursive Top-Down Production For Sentence Generation With Latent Trees | SHAWN TAN et. al. | To this end, we present a dynamic programming algorithm that marginalises over latent binary tree structures with $N$ leaves, allowing us to compute the likelihood of a sequence of $N$ tokens under a latent tree model, which we maximise to train a recursive neural function. | CS.arxiv | 2020-10-09 |
| 80 | Token-level Adaptive Training For Neural Machine Translation | SHUHAO GU et. al. | In this paper, we explored target token-level adaptive objectives based on token frequencies to assign appropriate weights for each target token during training. | CS.arxiv | 2020-10-09 |
| 81 | Uncertainty-Aware Semantic Augmentation For Neural Machine Translation | XIANGPENG WEI et. al. | To address this problem, we propose uncertainty-aware semantic augmentation, which explicitly captures the universal semantic information among multiple semantically-equivalent source sentences and enhances the hidden representations with this information for better translations. | CS.arxiv | 2020-10-09 |
| 82 | MLQE-PE: A Multilingual Quality Estimation And Post-Editing Dataset | MARINA FOMICHEVA et. al. | We present MLQE-PE, a new dataset for Machine Translation (MT) Quality Estimation (QE) and Automatic Post-Editing (APE). | CS.arxiv | 2020-10-09 |
| 83 | Word Level Language Identification In English Telugu Code Mixed Data | SUNIL GUNDAPU et. al. | In this paper, we present a study of various models – Nave Bayes Classifier, Random Forest Classifier, Conditional Random Field (CRF), and Hidden Markov Model (HMM) for Language Identification in English – Telugu Code Mixed Data. | CS.arxiv | 2020-10-09 |
| 84 | Self-Paced Learning For Neural Machine Translation | YU WAN et. al. | Recent studies have proven that the training of neural machine translation (NMT) can be facilitated by mimicking the learning process of humans. | CS.arxiv | 2020-10-09 |
| 85 | Dynamic Context Selection For Document-level Neural Machine Translation Via Reinforcement Learning | XIAOMIAN KANG et. al. | To address this problem, we propose an effective approach to select dynamic context so that the document-level translation model can utilize the more useful selected context sentences to produce better translations. | CS.arxiv | 2020-10-08 |
| 86 | Learning To Evaluate Translation Beyond English: BLEURT Submissions To The WMT Metrics 2020 Shared Task | THIBAULT SELLAM et. al. | This paper describes our contribution to the WMT 2020 Metrics Shared Task, the main benchmark for automatic evaluation of translation. | CS.arxiv | 2020-10-08 |
| 87 | Transformer-GCRF: Recovering Chinese Dropped Pronouns With General Conditional Random Fields | JINGXUAN YANG et. al. | In this paper, we present a novel framework that combines the strength of Transformer network with General Conditional Random Fields (GCRF) to model the dependencies between pronouns in neighboring utterances. | CS.arxiv | 2020-10-07 |
| 88 | Detecting Fine-Grained Cross-Lingual Semantic Divergences Without Supervision By Learning To Rank | ELEFTHERIA BRIAKOU et. al. | We introduce a training strategy for multilingual BERT models by learning to rank synthetic divergent examples of varying granularity. | CS.arxiv | 2020-10-07 |
| 89 | Shallow-to-Deep Training For Neural Machine Translation | BEI LI et. al. | In this paper, we investigate the behavior of a well-tuned deep Transformer system. | CS.arxiv | 2020-10-07 |
| 90 | Leveraging Discourse Rewards For Document-Level Neural Machine Translation | INIGO JAUREGI UNANUE et. al. | Therefore, in this paper we propose a training approach that explicitly optimizes two established discourse metrics, lexical cohesion (LC) and coherence (COH), by using a reinforcement learning objective. | CS.arxiv | 2020-10-07 |
| 91 | TeaForN: Teacher-Forcing With N-grams | SEBASTIAN GOODMAN et. al. | Empirically, we show that TeaForN boosts generation quality on one Machine Translation benchmark, WMT 2014 English-French, and two News Summarization benchmarks, CNN/Dailymail and Gigaword. | CS.arxiv | 2020-10-07 |
| 92 | Dual Reconstruction: A Unifying Objective For Semi-Supervised Neural Machine Translation | WEIJIA XU et. al. | We introduce a novel dual reconstruction objective that provides a unified view of Iterative Back-Translation and Dual Learning. | CS.arxiv | 2020-10-07 |
| 93 | PyMT5: Multi-mode Translation Of Natural Language And Python Code With Transformers | COLIN B. CLEMENT et. al. | We present an analysis and modeling effort of a large-scale parallel corpus of 26 million Python methods and 7.7 million method-docstring pairs, demonstrating that for docstring and method generation, PyMT5 outperforms similarly-sized auto-regressive language models (GPT2) which were English pre-trained or randomly initialized. | CS.arxiv | 2020-10-07 |
| 94 | On The Sub-Layer Functionalities Of Transformer Decoder | YILIN YANG et. al. | In this work, we study how Transformer-based decoders leverage information from the source and target languages — developing a universal probe task to assess how information is propagated through each module of each decoder layer. | CS.arxiv | 2020-10-06 |
| 95 | If Beam Search Is The Answer, What Was The Question? | CLARA MEISTER et. al. | We frame beam search as the exact solution to a different decoding objective in order to gain insights into why high probability under a model alone may not indicate adequacy. | CS.arxiv | 2020-10-06 |
| 96 | On The Sparsity Of Neural Machine Translation Models | YONG WANG et. al. | Modern neural machine translation (NMT) models employ a large number of parameters, which leads to serious over-parameterization and typically causes the underutilization of computational resources. | CS.arxiv | 2020-10-06 |
| 97 | Why Skip If You Can Combine: A Simple Knowledge Distillation Technique For Intermediate Layers | YIMENG WU et. al. | In this paper, we target low-resource settings and evaluate our translation engines for Portuguese–English, Turkish–English, and English–German directions. | CS.arxiv | 2020-10-06 |
| 98 | Converting The Point Of View Of Messages Spoken To Virtual Assistants | ISABELLE G. LEE et. al. | We developed a rule-based model, which integrates a linear text classification model, part-of-speech tagging, and constituency parsing with rule-based transformation methods. We have publicly released our dataset, which is composed of 46,565 crowd-sourced samples. | CS.arxiv | 2020-10-06 |
| 99 | An Empirical Study Of Tokenization Strategies For Various Korean NLP Tasks | KYUBYONG PARK et. al. | In this paper, we test several tokenization strategies in order to answer our primary research question, that is, What is the best tokenization strategy for Korean NLP tasks? | CS.arxiv | 2020-10-06 |
| 100 | Multi-task Learning For Multilingual Neural Machine Translation | YIREN WANG et. al. | In this work, we propose a multi-task learning (MTL) framework that jointly trains the model with the translation task on bitext data and two denoising tasks on the monolingual data. | CS.arxiv | 2020-10-06 |
| 101 | WikiLingua: A New Benchmark Dataset For Cross-Lingual Abstractive Summarization | FAISAL LADHAK et. al. | We introduce WikiLingua, a large-scale, multilingual dataset for the evaluation of crosslingual abstractive summarization systems. | CS.arxiv | 2020-10-06 |
| 102 | Data Rejuvenation: Exploiting Inactive Training Examples For Neural Machine Translation | WENXIANG JIAO et. al. | In this work, we explore to identify the inactive training examples which contribute less to the model performance, and show that the existence of inactive examples depends on the data distribution. | CS.arxiv | 2020-10-06 |
| 103 | Pre-training Multilingual Neural Machine Translation By Leveraging Alignment Information | ZEHUI LIN et. al. | We propose mRASP, an approach to pre-train a universal multilingual neural machine translation model. | CS.arxiv | 2020-10-06 |
| 104 | Scene Graph Modification Based On Natural Language Commands | XUANLI HE et. al. | In this paper, we explore the novel problem of graph modification, where the systems need to learn how to update an existing scene graph given a new user’s command. | CS.arxiv | 2020-10-06 |
| 105 | We Don’t Speak The Same Language: Interpreting Polarization Through Machine Translation | ASHIQUR R. KHUDABUKHSH et. al. | In this paper, we present a new methodology that offers a fresh perspective on interpreting polarization through the lens of machine translation. | CS.arxiv | 2020-10-05 |
| 106 | Efficient Inference For Neural Machine Translation | YI-TE HSU et. al. | In this work, we look for the optimal combination of known techniques to optimize inference speed without sacrificing translation quality. | CS.arxiv | 2020-10-05 |
| 107 | Adversarial Grammatical Error Correction | VIPUL RAHEJA et. al. | In this work, we present an adversarial learning approach to GEC, using the generator-discriminator framework. | CS.arxiv | 2020-10-05 |
| 108 | On The Relevance Of Cross-project Learning With Nearest Neighbours For Commit Message Generation | KHASHAYAR ETEMADI et. al. | In this paper, we show that NNGen does not take advantage of cross-project learning in the majority of the cases. | CS.arxiv | 2020-10-05 |
| 109 | A Streaming Approach For Efficient Batched Beam Search | KEVIN YANG et. al. | We propose an efficient batching strategy for variable-length decoding on GPU architectures. | CS.arxiv | 2020-10-05 |
| 110 | Improving AMR Parsing With Sequence-to-Sequence Pre-training | DONGQIN XU et. al. | In this paper, we focus on sequence-to-sequence (seq2seq) AMR parsing and propose a seq2seq pre-training approach to build pre-trained models in both single and joint way on three relevant tasks, i.e., machine translation, syntactic parsing, and AMR parsing itself. | CS.arxiv | 2020-10-05 |
| 111 | Participatory Research For Low-resourced Machine Translation: A Case Study In African Languages | WILHELMINA NEKOTO et. al. | In this paper, we focus on the task of Machine Translation (MT), that plays a crucial role for information accessibility and communication worldwide. | CS.arxiv | 2020-10-05 |
| 112 | Inference Strategies For Machine Translation With Conditional Masking | JULIA KREUTZER et. al. | We identify a thresholding strategy that has advantages over the standard mask-predict algorithm, and provide analyses of its behavior on machine translation tasks. | CS.arxiv | 2020-10-05 |
| 113 | X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset | ANGEL DAZA et. al. | In this work, we propose a method to automatically construct an SRL corpus that is parallel in four languages: English, French, German, Spanish, with unified predicate and role annotations that are fully comparable across languages. | CS.arxiv | 2020-10-05 |
| 114 | Improving Target-side Lexical Transfer In Multilingual Neural Machine Translation | LUYU GAO et. al. | In this paper, we aim to improve the effectiveness of multilingual transfer for NMT models that translate \emph{into} the LRL, by designing a better decoder word embedding. | CS.arxiv | 2020-10-04 |
| 115 | Leveraging Multilingual News Websites For Building A Kurdish Parallel Corpus | SINA AHMADI et. al. | In an attempt to create parallel corpora for the Kurdish language, in this paper, we describe our approach in retrieving potentially-alignable news articles from multi-language websites and manually align them across dialects and languages based on lexical similarity and transliteration of scripts. We present a corpus containing 12,327 translation pairs in the two major dialects of Kurdish, Sorani and Kurmanji. | CS.arxiv | 2020-10-04 |
| 116 | Unsupervised Cross-lingual Image Captioning | JIAHUI GAO et. al. | In this paper, we present a novel unsupervised method to generate image captions without using any caption corpus. | CS.arxiv | 2020-10-03 |
| 117 | Syntax Representation In Word Embeddings And Neural Networks — A Survey | TOMASZ LIMISIEWICZ et. al. | We describe which pre-trained models and representations of language are best suited for transfer to syntactic tasks. | CS.arxiv | 2020-10-02 |
| 118 | Nearest Neighbor Machine Translation | URVASHI KHANDELWAL et. al. | We introduce $k$-nearest-neighbor machine translation ($k$NN-MT), which predicts tokens with a nearest neighbor classifier over a large datastore of cached examples, using representations from a neural translation model for similarity search. | CS.arxiv | 2020-10-01 |
| 119 | WeChat Neural Machine Translation Systems For WMT20 | FANDONG MENG et. al. | In our experiments, we employ data selection, several synthetic data generation approaches (i.e., back-translation, knowledge distillation, and iterative in-domain knowledge transfer), advanced finetuning approaches and self-bleu based model ensemble. | CS.arxiv | 2020-10-01 |
| 120 | On Romanization For Model Transfer Between Scripts In Neural Machine Translation | CHANTAL AMRHEIN et. al. | We explore the benefit of romanization in this scenario. | CS.arxiv | 2020-09-30 |
| 121 | Learning Hard Retrieval Cross Attention For Transformer | HONGFEI XU et. al. | In this paper, we accelerate the inference of the scaled dot-product attention in another perspective. | CS.arxiv | 2020-09-30 |
| 122 | A Simple But Tough-to-Beat Data Augmentation Approach For Natural Language Understanding And Generation | DINGHAN SHEN et. al. | In this paper, we introduce a set of simple yet effective data augmentation strategies dubbed cutoff, where part of the information within an input sentence is erased to yield its restricted views (during the fine-tuning stage). | CS.arxiv | 2020-09-29 |
| 123 | Can Automatic Post-Editing Improve NMT? | SHAMIL CHOLLAMPATT et. al. | Automatic post-editing (APE) aims to improve machine translations, thereby reducing human post-editing effort. We release this new corpus under CC BY-NC-SA 4.0 license at https://github.com/shamilcm/pedra. | CS.arxiv | 2020-09-29 |
| 124 | Incomplete Utterance Rewriting As Semantic Segmentation | QIAN LIU et. al. | In this paper, we present a novel and extensive approach, which formulates it as a semantic segmentation task. | CS.arxiv | 2020-09-28 |
| 125 | Neural Baselines For Word Alignment | ANH KHOA NGO HO et. al. | In this work, we study and comprehensively evaluate neural models for unsupervised word alignment for four language pairs, contrasting several variants of neural models. | CS.arxiv | 2020-09-28 |
| 126 | Generative Latent Neural Models For Automatic Word Alignment | ANH KHOA NGO HO et. al. | In this paper, we study these models for the task of word alignment and propose and assess several evolutions of a vanilla variational autoencoders. | CS.arxiv | 2020-09-28 |
| 127 | Deep Transformers With Latent Depth | XIAN LI et. al. | We present a probabilistic framework to automatically learn which layer(s) to use by learning the posterior distributions of layer selection. | CS.arxiv | 2020-09-28 |
| 128 | Aspects Of Terminological And Named Entity Knowledge Within Rule-Based Machine Translation Models For Under-Resourced Neural Machine Translation Scenarios | DANIEL TORREGROSA et. al. | In this paper, we describe different approaches to leverage the information contained in rule-based machine translation systems to improve a corpus-based one, namely, a neural machine translation model, with a focus on a low-resource scenario. | CS.arxiv | 2020-09-28 |
| 129 | Automatic Arabic Dialect Identification Systems For Written Texts: A Survey | MAHA J. ALTHOBAITI | In this paper, we present a comprehensive survey of Arabic dialect identification research in written texts. | CS.arxiv | 2020-09-26 |
| 130 | XTE: Explainable Text Entailment | VIVIAN S. SILVA et. al. | In this work, we introduce XTE – Explainable Text Entailment – a novel composite approach for recognizing text entailment which analyzes the entailment pair to decide whether it must be resolved syntactically or semantically. | CS.arxiv | 2020-09-25 |
| 131 | Harnessing Multilinguality In Unsupervised Machine Translation For Rare Languages | XAVIER GARCIA et. al. | In this work, we show that multilinguality is critical to making unsupervised systems practical for low-resource settings. | CS.arxiv | 2020-09-23 |
| 132 | Multi-Pass Transformer For Machine Translation | PENG GAO et. al. | In contrast with previous approaches where information flows only towards deeper layers of a stack, we consider a multi-pass transformer (MPT) architecture in which earlier layers are allowed to process information in light of the output of later layers. | CS.arxiv | 2020-09-23 |
| 133 | KoBE: Knowledge-Based Machine Translation Evaluation | ZORIK GEKHMAN et. al. | We propose a simple and effective method for machine translation evaluation which does not require reference translations. To foster further research, we release a dataset containing 1.8 million grounded entity mentions across 18 language pairs from the WMT19 metrics track data. | CS.arxiv | 2020-09-23 |
| 134 | Public Health Informatics: Proposing Causal Sequence Of Death Using Neural Machine Translation | YUANDA ZHU et. al. | To facilitate physicians in accurately reporting causes of death, we present an advanced AI approach to determine a chronically ordered sequence of clinical conditions that lead to death, based on decedent’s last hospital admission discharge record. | CS.arxiv | 2020-09-22 |
| 135 | Alleviating The Inequality Of Attention Heads For Neural Machine Translation | ZEWEI SUN et. al. | To tackle this problem, we propose a simple masking method: HeadMask, in two specific ways. | CS.arxiv | 2020-09-21 |
| 136 | Generative Imagination Elevates Machine Translation | QUANYU LONG et. al. | In this paper, we hypothesize that visual imagination via synthesizing visual representation from source text could help the neural model map two languages with different symbols, thus helps the translation task. | CS.arxiv | 2020-09-21 |
| 137 | TED: Triple Supervision Decouples End-to-end Speech-to-text Translation | QIANQIAN DONG et. al. | Inspired by neuroscience, humans have perception systems and cognitive systems to process different information, we propose TED, \textbf{T}ransducer-\textbf{E}ncoder-\textbf{D}ecoder, a unified framework with triple supervision to decouple the end-to-end speech-to-text translation task. | CS.arxiv | 2020-09-21 |
| 138 | SDST: Successive Decoding For Speech-to-text Translation | QIANQIAN DONG et. al. | To reduce the learning difficulty, we propose SDST, an integral framework with \textbf{S}uccessive \textbf{D}ecoding for end-to-end \textbf{S}peech-to-text \textbf{T}ranslation task. | CS.arxiv | 2020-09-21 |
| 139 | UCD-CS At W-NUT 2020 Shared Task-3: A Text To Text Approach For COVID-19 Event Extraction On Social Media | CONGCONG WANG et. al. | In this paper, we describe our approach in the shared task: COVID-19 event extraction from Twitter. | CS.arxiv | 2020-09-21 |
| 140 | Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, And New Datasets For Bengali-English Machine Translation | TAHMID HASAN et. al. | In this work, we build a customized sentence segmenter for Bengali and propose two novel methods for parallel corpus creation on low-resource setups: aligner ensembling and batch filtering. We release the segmenter, parallel corpus, and the evaluation set, thus elevating Bengali from its low-resource status. | CS.arxiv | 2020-09-20 |
| 141 | Softmax Tempering For Training Neural Machine Translation Models | RAJ DABRE et. al. | To address this issue, we propose to divide the logits by a temperature coefficient, prior to applying softmax, during training. | CS.arxiv | 2020-09-20 |
| 142 | Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models | SUBHAJIT NASKAR et. al. | To benefit from this observation, we train an energy-based model to mimic the behavior of the task measure (i.e., the energy-based model assigns lower energy to samples with higher BLEU score), which is resulted in a re-ranking algorithm based on the samples drawn from NMT: energy-based re-ranking (EBR). | CS.arxiv | 2020-09-19 |
| 143 | Towards Computational Linguistics In Minangkabau Language: Studies On Sentiment Analysis And Machine Translation | FAJRI KOTO et. al. | In this work, we release two Minangkabau corpora: sentiment analysis and machine translation that are harvested and constructed from Twitter and Wikipedia. | CS.arxiv | 2020-09-19 |
| 144 | Weight Distillation: Transferring The Knowledge In Neural Network Parameters | YE LIN et. al. | We propose Weight Distillation to transfer the knowledge in the large network parameters through a parameter generator. | CS.arxiv | 2020-09-18 |
| 145 | Computer Assisted Translation With Neural Quality Estimation And Automatic Post-Editing | JIAYI WANG et. al. | In this paper, we propose an end-to-end deep learning framework of the quality estimation and automatic post-editing of the machine translation output. | CS.arxiv | 2020-09-18 |
| 146 | Long-Short Term Masking Transformer: A Simple But Effective Baseline For Document-level Neural Machine Translation | PEI ZHANG et. al. | In this paper, we research extensively the pros and cons of the standard transformer in document-level translation, and find that the auto-regressive property can simultaneously bring both the advantage of the consistency and the disadvantage of error accumulation. | CS.arxiv | 2020-09-18 |
| 147 | COMET: A Neural Framework For MT Evaluation | RICARDO REI et. al. | We present COMET, a neural framework for training multilingual machine translation evaluation models which obtains new state-of-the-art levels of correlation with human judgements. | CS.arxiv | 2020-09-18 |
| 148 | Unsupervised Parallel Corpus Mining On Web Data | GUOKUN LAI et. al. | In this paper, we present a pipeline to mine the parallel corpus from the Internet in an unsupervised manner. | CS.arxiv | 2020-09-17 |
| 149 | Code-switching Pre-training For Neural Machine Translation | ZHEN YANG et. al. | This paper proposes a new pre-training method, called Code-Switching Pre-training (CSP for short) for Neural Machine Translation (NMT). | CS.arxiv | 2020-09-17 |
| 150 | Multilingual Music Genre Embeddings For Effective Cross-Lingual Music Item Annotation | ELENA V. EPURE et. al. | Here, by learning multilingual music genre embeddings, we enable cross-lingual music genre translation without relying on a parallel corpus. We publicly release the new multilingual data and code. | CS.arxiv | 2020-09-16 |
| 151 | Knowledge Graphs For Multilingual Language Translation And Generation | DIEGO MOUSSALLEM | In this thesis, we focus on the use of KGs for machine translation and the generation of texts to deal with the problems caused by entities and consequently enhance the quality of automatically generated texts. | CS.arxiv | 2020-09-16 |
| 152 | Reusing A Pretrained Language Model On Languages With Limited Corpora For Unsupervised NMT | ALEXANDRA CHRONOPOULOU et. al. | We present an effective approach that reuses an LM that is pretrained only on the high-resource language. | CS.arxiv | 2020-09-16 |
| 153 | Dissecting Lottery Ticket Transformers: Structural And Behavioral Study Of Sparse Neural Machine Translation | RAJIV MOVVA et. al. | Analysis of internal activations reveals that higher layers diverge most over the course of pruning, gradually becoming less complex than their dense counterparts. | CS.arxiv | 2020-09-16 |
| 154 | Text Generation By Learning From Off-Policy Demonstrations | RICHARD YUANZHE PANG et. al. | We propose GOLD (generation by off-policy learning from demonstrations): an algorithm that learns from the off-policy demonstrations by importance weighting and does not suffer from degenerative solutions. | CS.arxiv | 2020-09-16 |
| 155 | Graph-to-Sequence Neural Machine Translation | SUFENG DUAN et. al. | In detail, we propose a graph-based SAN-based NMT model called Graph-Transformer by capturing information of subgraphs of different orders in every layers. | CS.arxiv | 2020-09-16 |
| 156 | Attention-Aware Inference For Neural Abstractive Summarization | YE MA et. al. | Inspired by Google’s Neural Machine Translation (NMT) \cite{Wu2016Google} that models the one-to-one alignment in translation tasks with an optimal uniform attention distribution during the inference, this study proposes an attention-aware inference algorithm for Neural Abstractive Summarization (NAS) to regulate generated summaries to attend to source paragraphs/sentences with the optimal coverage. | CS.arxiv | 2020-09-15 |
| 157 | Simultaneous Machine Translation With Visual Context | OZAN CAGLAYAN et. al. | In this paper, we seek to understand whether the addition of visual information can compensate for the missing source context. | CS.arxiv | 2020-09-15 |
| 158 | Extremely Low Bit Transformer Quantization For On-Device Neural Machine Translation | INSOO CHUNG et. al. | Correspondingly, we propose a mixed precision quantization strategy to represent Transformer weights by an extremely low number of bits (e.g., under 3 bits). | CS.arxiv | 2020-09-15 |
| 159 | Iterative Refinement In The Continuous Space For Non-Autoregressive Neural Machine Translation | JASON LEE et. al. | We propose an efficient inference procedure for non-autoregressive machine translation that iteratively refines translation purely in the continuous space. | CS.arxiv | 2020-09-15 |
| 160 | Development Of A Dataset And A Deep Learning Baseline Named Entity Recognizer For Three Low Resource Languages: Bhojpuri, Maithili And Magahi | RAJESH KUMAR MUNDOTIYA et. al. | The lower baseline F1-scores from the NER tool obtained by using Conditional Random Fields models are 96.73 for Bhojpuri, 93.33 for Maithili and 95.04 for Magahi. | CS.arxiv | 2020-09-14 |
| 161 | Combining Word And Character Vector Representation On Neural Machine Translation | K. M. SHAHIH et. al. | This paper describes combinations of word vector representation and character vector representation in English-Indonesian neural machine translation (NMT). | CS.arxiv | 2020-09-13 |
| 162 | Robust Neural Machine Translation: Modeling Orthographic And Interpunctual Variation | TOMS BERGMANIS et. al. | We propose a simple generative noise model to generate adversarial examples of ten different types. | CS.arxiv | 2020-09-11 |
| 163 | On Target Segmentation For Direct Speech Translation | MATTIA ANTONINO DI GANGI et. al. | In this work, we perform an extensive comparison of the two methods on three benchmarks covering 8 language directions and multilingual training. | CS.arxiv | 2020-09-10 |
| 164 | Central Yup’ik And Machine Translation Of Low-Resource Polysynthetic Languages | CHRISTOPHER LIU et. al. | We trained a seq2seq neural machine translation model with attention to translate Yup’ik input into English. | CS.arxiv | 2020-09-08 |
| 165 | TransModality: An End2End Fusion Method With Transformer For Multimodal Sentiment Analysis | ZILONG WANG et. al. | Enlightened by recent success of Transformer in the area of machine translation, we propose a new fusion method, TransModality, to address the task of multimodal sentiment analysis. | CS.arxiv | 2020-09-07 |
| 166 | Why Not Simply Translate? A First Swedish Evaluation Benchmark For Semantic Similarity | TIM ISBISTER et. al. | This paper presents the first Swedish evaluation benchmark for textual semantic similarity. | CS.arxiv | 2020-09-07 |
| 167 | Recent Trends In The Use Of Deep Learning Models For Grammar Error Handling | MINA NAGHSHNEJAD et. al. | In this survey we focus on two main DL approaches for GEH: neural machine translation models and editor models. | CS.arxiv | 2020-09-04 |
| 168 | Modeling Global Body Configurations In American Sign Language | NICHOLAS WILKINS et. al. | The main contributions of this paper are | CS.arxiv | 2020-09-03 |
| 169 | Multi-channel Transformers For Multi-articulatory Sign Language Translation | NECATI CIHAN CAMGOZ et. al. | In this paper we tackle the multi-articulatory sign language translation task and propose a novel multi-channel transformer architecture. | CS.arxiv | 2020-09-01 |
| 170 | Discovering Bilingual Lexicons In Polyglot Word Embeddings | ASHIQUR R. KHUDABUKHSH et. al. | In this work, we utilize a single Skip-gram model trained on a multilingual corpus yielding polyglot word embeddings, and present a novel finding that a surprisingly simple constrained nearest-neighbor sampling technique in this embedding space can retrieve bilingual lexicons, even in harsh social media data sets predominantly written in English and Romanized Hindi and often exhibiting code switching. | CS.arxiv | 2020-08-30 |
| 171 | The Impact Of Indirect Machine Translation On Sentiment Classification | ALBERTO PONCELAS et. al. | In this work, we propose employing a machine translation (MT) system to translate customer feedback into another language to investigate in which cases translated sentences can have a positive or negative impact on an automatic sentiment classifier. | CS.arxiv | 2020-08-25 |
| 172 | Learn To Talk Via Proactive Knowledge Transfer | QING SUN et. al. | In this paper, we provide an in-depth analysis of KL-divergence minimization in Forward and Backward orders, which shows that learners are reinforced via on-policy learning in Backward. | CS.arxiv | 2020-08-23 |
| 173 | Neural Machine Translation Without Embeddings | URI SHAHAM et. al. | Could NLP models work without the embedding component? | CS.arxiv | 2020-08-21 |
| 174 | Unsupervised Translation Via Hierarchical Anchoring: Functional Mapping Of Places Across Cities | TAKAHIRO YABE et. al. | We address this problem by proposing an unsupervised translation method that translates embeddings by exploiting common hierarchical structures that exist across imbalanced domains. | CS.kdd | 2020-08-21 |
| 175 | Semantic Relation Preserving Knowledge Distillation For Image-to-Image Translation | ZEQI LI et. al. | In this work, we propose a novel method to address this problem by applying knowledge distillation together with distillation of a semantic relation preserving matrix. | CS.eccv | 2020-08-21 |
| 176 | Lite Training Strategies For Portuguese-English And English-Portuguese Translation | ALEXANDRE LOPES et. al. | In this work, we investigate the use of pre-trained models, such as T5 for Portuguese-English and English-Portuguese translation tasks using low-cost hardware. | CS.arxiv | 2020-08-20 |
| 177 | Transformer Based Multilingual Document Embedding Model | WEI LI et. al. | This paper presents a transformer-based sentence/document embedding model, T-LASER, which makes three significant improvements. | CS.arxiv | 2020-08-19 |
| 178 | Very Deep Transformers For Neural Machine Translation | XIAODONG LIU et. al. | We explore the application of very deep Transformer models for Neural Machine Translation (NMT). | CS.arxiv | 2020-08-18 |
| 179 | Glancing Transformer For Non-Autoregressive Neural Machine Translation | LIHUA QIAN et. al. | In this paper, we propose Glancing Transformer (GLAT) to address the above disadvantages, which reduces the difficulty of learning simultaneous generation and introduces explicit target language modeling in the non-autoregressive setting at the same time. | CS.arxiv | 2020-08-18 |
| 180 | BUT-FIT At SemEval-2020 Task 4: Multilingual Commonsense | JOSEF JON et. al. | This paper describes work of the BUT-FIT’s team at SemEval 2020 Task 4 – Commonsense Validation and Explanation. | CS.arxiv | 2020-08-17 |
| 181 | Compositional Generalization Via Neural-Symbolic Stack Machines | XINYUN CHEN et. al. | To tackle this issue, we propose the Neural-Symbolic Stack Machine (NeSS). | CS.arxiv | 2020-08-15 |
| 182 | Approaching Neural Chinese Word Segmentation As A Low-Resource Machine Translation Task | PINZHEN CHEN et. al. | In this work, we apply the best practices from low-resource neural machine translation to Chinese word segmentation. | CS.arxiv | 2020-08-12 |
| 183 | The Sockeye 2 Neural Machine Translation Toolkit At AMTA 2020 | TOBIAS DOMHAN et. al. | We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. | CS.arxiv | 2020-08-11 |
| 184 | Retrieval Guided Unsupervised Multi-domain Image-to-Image Translation | RAUL GOMEZ et. al. | In this paper we propose the use of an image retrieval system to assist the image-to-image translation task. | CS.arxiv | 2020-08-11 |
| 185 | Paraphrase Generation As Zero-Shot Multilingual Translation: Disentangling Semantic Similarity From Lexical And Syntactic Diversity | BRIAN THOMPSON et. al. | We introduce a simple paraphrase generation algorithm which discourages the production of n-grams that are present in the input. | CS.arxiv | 2020-08-11 |
| 186 | On Learning Language-Invariant Representations For Universal Machine Translation | HAN ZHAO et. al. | In this paper, we formally prove certain impossibilities of this endeavour in general, as well as prove positive results in the presence of additional (but natural) structure of data. | CS.arxiv | 2020-08-11 |
| 187 | A Parallel Evaluation Data Set Of Software Documentation With Document Structure Annotation | BIANKA BUSCHBECK et. al. | We provide insights into the origin and creation, the particularities and characteristics of the data set. | CS.arxiv | 2020-08-11 |
| 188 | Revisiting Low Resource Status Of Indian Languages In Machine Translation | JERIN PHILIP et. al. | The main contribution towards this effort is to obtain an incremental method that uses the above pipeline to iteratively improve the size of the corpus as well as improve each of the components of our system. | CS.arxiv | 2020-08-11 |
| 189 | Data Weighted Training Strategies For Grammatical Error Correction | JARED LICHTARGE et. al. | In this work, we perform an empirical study to discover how to best incorporate delta-log-perplexity, a type of example scoring, into a training schedule for GEC. | CS.arxiv | 2020-08-06 |
| 190 | A Multilingual Neural Machine Translation Model For Biomedical Data | ALEXANDRE BÉRARD et. al. | We also release a test set of biomedical text for Korean-English. | CS.arxiv | 2020-08-06 |
| 191 | Contextualized Translation Of Automatically Segmented Speech | MARCO GAIDO et. al. | In this paper, instead, we address the issue in the model, making it more robust to a different, potentially sub-optimal segmentation. | CS.arxiv | 2020-08-05 |
| 192 | Designing The Business Conversation Corpus | MATĪSS RIKTERS et. al. | In this paper, we aim to boost the machine translation quality of conversational texts by introducing a newly constructed Japanese-English business conversation parallel corpus. | CS.arxiv | 2020-08-05 |
| 193 | A Survey Of Orthographic Information In Machine Translation | BHARATHI RAJA CHAKRAVARTHI et. al. | We describe previous work in this area, discussing what underlying assumptions were made, and showing how orthographic knowledge improves the performance of machine translation of under-resourced languages. | CS.arxiv | 2020-08-04 |
| 194 | Multilingual Translation With Extensible Multilingual Pretraining And Finetuning | YUQING TANG et. al. | In this work, we show that multilingual translation models can be created through multilingual finetuning. Finally, we create the ML50 benchmark, covering low, mid, and high resource languages, to facilitate reproducible research by standardizing training and evaluation data. | CS.arxiv | 2020-08-02 |
| 195 | On Learning Universal Representations Across Languages | XIANGPENG WEI et. al. | In this work, we extend these approaches to learn sentence-level representations, and show the effectiveness on cross-lingual understanding and generation. | CS.arxiv | 2020-07-31 |
| 196 | Preparation Of Sentiment Tagged Parallel Corpus And Testing Its Effect On Machine Translation | SAINIK KUMAR MAHATA et. al. | In the current work, we explore the enrichment in the machine translation output when the training parallel corpus is augmented with the introduction of sentiment analysis. | CS.arxiv | 2020-07-28 |
| 197 | TensorCoder: Dimension-Wise Attention Via Tensor Representation For Natural Language Modeling | SHUAI ZHANG et. al. | In this paper, we propose a dimension-wise attention mechanism based on which a novel language modeling approach (namely TensorCoder) can be developed. | CS.arxiv | 2020-07-28 |
| 198 | A System For Worldwide COVID-19 Information Aggregation | AKIKO AIZAWA et. al. | We build a system for worldwide COVID-19 information aggregation containing reliable articles from 10 regions in 7 languages sorted by topics. | CS.arxiv | 2020-07-27 |
| 199 | Training Effective Neural CLIR By Bridging The Translation Gap | HAMED BONAB et. al. | We introduce Smart Shuffling, a cross-lingual embedding (CLE) method that draws from statistical word alignment approaches to leverage dictionaries, producing dense representations that are significantly more effective for cross-language information retrieval (CLIR) than prior CLE methods. | CS.sigir | 2020-07-25 |
| 200 | Searching The Web For Cross-lingual Parallel Data | AHMED EL-KISHKY et. al. | We introduce techniques for searching for cross-lingual parallel data based on language, content, and other metadata. | CS.sigir | 2020-07-25 |
| 201 | Relevance Transformer: Generating Concise Code Snippets With Relevance Feedback | CARLOS GEMMELL et. al. | In this work we introduce and study modern Transformer architectures for this task. | CS.sigir | 2020-07-25 |
| 202 | Combining Contextualized And Non-contextualized Query Translations To Improve CLIR | SURAJ NAIR et. al. | This paper presents evidence that combining such context-dependent translation probabilities with context-independent translation probabilities learned from the same parallel corpus can yield improvements in the effectiveness of cross-language ranked retrieval. | CS.sigir | 2020-07-25 |
| 203 | Consistent Transcription And Translation Of Speech | MATTHIAS SPERBER et. al. | We introduce a methodology to evaluate consistency and compare several modeling approaches, including the traditional cascaded approach and end-to-end models. | CS.arxiv | 2020-07-24 |
| 204 | JUNLP@SemEval-2020 Task 9:Sentiment Analysis Of Hindi-English Code Mixed Data Using Grid Search Cross Validation | AVISHEK GARAIN et. al. | In this work, we focus on working out a plausible solution to the domain of Code-Mixed Sentiment Analysis. | CS.arxiv | 2020-07-24 |
| 205 | SBAT: Video Captioning With Sparse Boundary-Aware Transformer | TAO JIN et. al. | In this paper, we focus on the problem of applying the transformer structure to video captioning effectively. | CS.arxiv | 2020-07-23 |
| 206 | Bridging The Gap Between Training And Inference For Neural Machine Translation (Extended Abstract) | WEN ZHANG et. al. | In this paper, we address these issues by sampling context words not only from the ground truth sequence but also from the predicted sequence during training. | CS.ijcai | 2020-07-21 |
| 207 | Non-Autoregressive Image Captioning With Counterfactuals-Critical Multi-Agent Learning | LONGTENG GUO et. al. | In this paper, we propose a Non-Autoregressive Image Captioning (NAIC) model with a novel training paradigm: Counterfactuals-critical Multi-Agent Learning (CMAL). | CS.ijcai | 2020-07-21 |
| 208 | Modeling Voting For System Combination In Machine Translation | XUANCHENG HUANG et. al. | In this work, we propose an approach to modeling voting for system combination in machine translation. | CS.ijcai | 2020-07-21 |
| 209 | Emoji-Powered Representation Learning For Cross-Lingual Sentiment Classification (Extended Abstract) | ZHENPENG CHEN et. al. | In this paper, we employ emojis, which are widely available in many languages, as a new channel to learn both the cross-language and the language-specific sentiment patterns. | CS.ijcai | 2020-07-21 |
| 210 | Efficient Context-Aware Neural Machine Translation With Layer-Wise Weighting And Input-Aware Gating | HONGFEI XU et. al. | In this paper, we propose to make the most of layers pre-trained on sentence-level data in contextual representation learning, reusing representations from the sentence-level Transformer and significantly reducing the cost of incorporating contexts in translation. | CS.ijcai | 2020-07-21 |
| 211 | Lexical-Constraint-Aware Neural Machine Translation Via Data Augmentation | GUANHUA CHEN et. al. | In response to these problems, we present a conceptually simple and empirically effective data augmentation approach in lexical constrained neural machine translation. | CS.ijcai | 2020-07-21 |
| 212 | Task-Level Curriculum Learning For Non-Autoregressive Neural Machine Translation | JINGLIN LIU et. al. | To smooth the shift from AT training to NAT training, in this paper, we introduce semi-autoregressive translation (SAT) as intermediate tasks. | CS.ijcai | 2020-07-21 |
| 213 | Knowledge Graphs Enhanced Neural Machine Translation | YANG ZHAO et. al. | To improve the translation quality of these entities, in this paper we propose a novel KGs enhanced NMT method. | CS.ijcai | 2020-07-21 |
| 214 | Neural Machine Translation With Error Correction | KAITAO SONG et. al. | In this paper, we introduce an error correction mechanism into NMT, which corrects the error information in the previous generated tokens to better predict the next token. | CS.arxiv | 2020-07-21 |
| 215 | CoVoST 2 And Massively Multilingual Speech-to-Text Translation | CHANGHAN WANG et. al. | CoVoST 2 And Massively Multilingual Speech-to-Text Translation | CS.arxiv | 2020-07-20 |
| 216 | Voice@SRIB At SemEval-2020 Task 9 And 12: Stacked Ensembling Method For Sentiment And Offensiveness Detection In Social Media | ABHISHEK SINGH et. al. | In this paper, we describe different models we used, using the external dataset to train embeddings, ensembling methods for Sentimix, and OffensEval tasks. | CS.arxiv | 2020-07-20 |
| 217 | Translation Between Waves, Wave2wave | TSUYOSHI OKITA et. al. | This paper proposes a new variant of neural machine translation seq2seq to deal with continuous signal waves by introducing the window-based (inverse-) representation to adaptively represent partial shapes of waves and the iterative back-translation model for high-dimensional data. | CS.arxiv | 2020-07-20 |
| 218 | A Novel Graph-based Multi-modal Fusion Encoder For Neural Machine Translation | YONGJING YIN et. al. | To deal with this issue, in this paper, we propose a novel graph-based multi-modal fusion encoder for NMT. | CS.arxiv | 2020-07-17 |
| 219 | A Multilingual Parallel Corpora Collection Effort For Indian Languages | SHASHANK SIRIPRAGADA et. al. | Alongside, we report on the methods of constructing such corpora using tools enabled by recent advances in machine translation and cross-lingual retrieval using deep neural network based methods. We also provide a separate test corpus compiled from an independent online source that can be independently used for validating the performance in 10 Indian languages. | CS.arxiv | 2020-07-15 |
| 220 | Dual Past And Future For Neural Machine Translation | JIANHAO YAN et. al. | In this paper, we present a novel dual framework that leverages both source-to-target and target-to-source NMT models to provide a more direct and accurate supervision signal for the Past and Future modules. | CS.arxiv | 2020-07-15 |
| 221 | Transformer With Depth-Wise LSTM | HONGFEI XU et. al. | In this paper, we suggest that the residual connection has its drawbacks, and propose to train Transformers with the depth-wise LSTM which regards outputs of layers as steps in time series instead of residual connections, under the motivation that the vanishing gradient problem suffered by deep networks is the same as recurrent networks applied to long sequences, while LSTM (Hochreiter and Schmidhuber, 1997) has been proven of good capability in capturing long-distance relationship, and its design may alleviate some drawbacks of residual connections while ensuring the convergence. | CS.arxiv | 2020-07-13 |
| 222 | Aligned Cross Entropy For Non-Autoregressive Machine Translation | MARJAN GHAZVININEJAD et. al. | In this paper, we propose aligned cross entropy (AXE) as an alternate loss function for training of non-autoregressive models. | CS.icml | 2020-07-11 |
| 223 | Improving Transformer Optimization Through Better Initialization | XIAO SHI HUANG et. al. | In this work our contributions are two-fold. We first investigate and empirically validate the source of optimization problems in encoder-decoder Transformer architecture.We then propose a new weight initialization scheme with theoretical justification, which enables training without warmup or layer normalization. | CS.icml | 2020-07-11 |
| 224 | Non-autoregressive Translation With Disentangled Context Transformer | JUNGO KASAI et. al. | We propose an attention-masking based model, called Disentangled Context (DisCo) transformer, that simultaneously generates all tokens given different contexts. | CS.icml | 2020-07-11 |
| 225 | Sequence Generation With Mixed Representations | LIJUN WU et. al. | In this work, we propose to leverage the mixed representations from different tokenization methods for sequence generation tasks, in order to boost the model performance with unique characteristics and advantages of individual tokenization methods. | CS.icml | 2020-07-11 |
| 226 | An EM Approach To Non-autoregressive Conditional Sequence Generation | ZHIQING SUN et. al. | This paper proposes a new approach that jointly optimizes both AR and NAR models in a unified Expectation-Maximization (EM) framework. | CS.icml | 2020-07-11 |
| 227 | Pragmatic Information In Translation: A Corpus-based Study Of Tense And Mood In English And German | ANITA RAMM et. al. | Human translators do not find this correspondence easy, and as we will show through careful analysis, there are no simplistic ways to map tense and mood from one language to another. | CS.arxiv | 2020-07-10 |
| 228 | Learn To Use Future Information In Simultaneous Translation | XUEQING WU et. al. | Based on this observation, we propose a framework that automatically learns how much future information to use in training for simultaneous NMT. | CS.arxiv | 2020-07-10 |
| 229 | Scb-mt-en-th-2020: A Large English-Thai Parallel Corpus | LALITA LOWPHANSIRIKUL et. al. | The primary objective of our work is to build a large-scale English-Thai dataset for machine translation. We construct an English-Thai machine translation dataset with over 1 million segment pairs, curated from various sources, namely news, Wikipedia articles, SMS messages, task-based dialogs, web-crawled data and government documents. | CS.arxiv | 2020-07-07 |
| 230 | Bilingual Dictionary Based Neural Machine Translation Without Using Parallel Sentences | XIANGYU DUAN et. al. | In this paper, we propose a new task of machine translation (MT), which is based on no parallel sentences but can refer to a ground-truth bilingual dictionary. | CS.arxiv | 2020-07-06 |
| 231 | Text Data Augmentation: Towards Better Detection Of Spear-phishing Emails | MEHDI REGINA et. al. | Motivated by a business application of Business Email Compromise (BEC) detection, we propose a corpus and task agnostic text augmentation framework combining different methods, utilizing BERT language model, multi-step back-translation and heuristics. | CS.arxiv | 2020-07-04 |
| 232 | El Departamento De Nosotros: How Machine Translated Corpora Affects Language Models In MRC Tasks | MARIA KHVALCHIK et. al. | In this work, we study the caveats of applying directly translated corpora for fine-tuning LMs for downstream natural language processing tasks and demonstrate that careful curation along with post-processing lead to improved performance and overall LMs robustness. | CS.arxiv | 2020-07-03 |
| 233 | Reading Comprehension In Czech Via Machine Translation And Cross-lingual Transfer | KATEŘINA MACKOVÁ et. al. | The cross-lingual transfer approach is very flexible and provides a reading comprehension in any language, for which we have enough monolingual raw texts. | CS.arxiv | 2020-07-03 |
| 234 | GShard: Scaling Giant Models With Conditional Computation And Automatic Sharding | DMITRY LEPIKHIN et. al. | We demonstrate that such a giant model can efficiently be trained on 2048 TPU v3 accelerators in 4 days to achieve far superior quality for translation from 100 languages to English compared to the prior art. | CS.arxiv | 2020-06-30 |
| 235 | Traceability Support For Multi-Lingual Software Projects | YALIN LIU et. al. | Due to the non-trivial costs of manually creating and maintaining links, many researchers have proposed automated approaches based on information retrieval techniques. | CS.arxiv | 2020-06-30 |
| 236 | Multi-Head Attention: Collaborate Instead Of Concatenate | JEAN-BAPTISTE CORDONNIER et. al. | Motivated by the observation that trained attention heads share common key/query projections, we propose a collaborative multi-head attention layer that enables heads to learn shared projections. | CS.arxiv | 2020-06-29 |
| 237 | Measuring Memorization Effect In Word-Level Neural Networks Probing | RUDOLF ROSA et. al. | In our work, we propose a simple general method for measuring the memorization effect, based on a symmetric selection of comparable sets of test words seen versus unseen in training. | CS.arxiv | 2020-06-29 |
| 238 | Simplifying Models With Unlabeled Output Data | SANG MICHAEL XIE et. al. | In this paper, we present predict-and-denoise, a framework that can leverage unlabeled outputs. | CS.arxiv | 2020-06-29 |
| 239 | Self-Attention Networks For Intent Detection | SEVINJ YOLCHUYEVA et. al. | In this paper, we present a novel intent detection system which is based on a self-attention network and a Bi-LSTM. | CS.arxiv | 2020-06-28 |
| 240 | A Deep Reinforced Model For Zero-Shot Cross-Lingual Summarization With Bilingual Semantic Similarity Rewards | ZI-YI DOU et. al. | In this work, we propose an end-to-end cross-lingual text summarization model. | CS.arxiv | 2020-06-27 |
| 241 | Recurrent Quantum Neural Networks | JOHANNES BAUSCH | In this work we construct a quantum recurrent neural network (QRNN) with demonstrable performance on non-trivial tasks such as sequence learning and integer digit classification. | CS.arxiv | 2020-06-25 |
| 242 | THEaiTRE: Artificial Intelligence To Write A Theatre Play | RUDOLF ROSA et. al. | We present THEaiTRE, a starting project aimed at automatic generation of theatre play scripts. | CS.arxiv | 2020-06-25 |
| 243 | Graph Optimal Transport For Cross-Domain Alignment | LIQUN CHEN et. al. | We propose Graph Optimal Transport (GOT), a principled framework that germinates from recent advances in Optimal Transport (OT). | CS.arxiv | 2020-06-25 |
| 244 | Learning Source Phrase Representations For Neural Machine Translation | HONGFEI XU et. al. | The Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the performance of Neural Machine Translation (NMT). | CS.arxiv | 2020-06-25 |
| 245 | Modeling Baroque Two-Part Counterpoint With Neural Machine Translation | ERIC P. NICHOLS et. al. | We propose a system for contrapuntal music generation based on a Neural Machine Translation (NMT) paradigm. | CS.arxiv | 2020-06-25 |
| 246 | Neural Machine Translation For Paraphrase Generation | ALEX SOKOLOV et. al. | In this work, we present an automatic natural language generation system, capable of generating both human-like interactions and annotations by the means of paraphrasing. | CS.arxiv | 2020-06-25 |
| 247 | Differentiable Window For Dynamic Local Attention | THANH-TUNG NGUYEN et. al. | We propose Differentiable Window, a new neural module and general purpose component for dynamic window selection. | CS.arxiv | 2020-06-24 |
| 248 | NLPContributions: An Annotation Scheme For Machine Reading Of Scholarly Contributions In Natural Language Processing Literature | JENNIFER D’SOUZA et. al. | In this article, we describe the outcomes of this pilot annotation phase. | CS.arxiv | 2020-06-23 |
| 249 | Keyframe Segmentation And Positional Encoding For Video-guided Machine Translation Challenge 2020 | TOSHO HIRASAWA et. al. | In this work, we presented our video-guided machine translation system in approaching the Video-guided Machine Translation Challenge 2020. | CS.arxiv | 2020-06-23 |
| 250 | Exploiting Non-Taxonomic Relations For Measuring Semantic Similarity And Relatedness In WordNet | MOHANNAD ALMOUSA et. al. | We propose a holistic poly-relational approach based on a new relation-based information content and non-taxonomic-based weighted paths to devise a comprehensive semantic similarity and relatedness measure. | CS.arxiv | 2020-06-22 |
| 251 | Self-Knowledge Distillation: A Simple Way For Better Generalization | KYUNGYUL KIM et. al. | In this work, we propose a simple yet effective regularization method named self-knowledge distillation (Self-KD), which progressively distills a model’s own knowledge to soften hard targets (i.e., one-hot vectors) during training. | CS.arxiv | 2020-06-22 |
| 252 | AdvAug: Robust Adversarial Augmentation For Neural Machine Translation | YONG CHENG et. al. | In this paper, we propose a new adversarial augmentation method for Neural Machine Translation (NMT). | CS.arxiv | 2020-06-21 |
| 253 | On Exposure Bias, Hallucination And Domain Shift In Neural Machine Translation | CHAOJUN WANG et. al. | In this paper, we link exposure bias to another well-known problem in NMT, namely the tendency to generate hallucinations under domain shift. | CS.acl | 2020-06-20 |
| 254 | Boosting Neural Machine Translation With Similar Translations | JITAO XU et. al. | This paper explores data augmentation methods for training Neural Machine Translation to make use of similar translations, in a comparable way a human translator employs fuzzy matches. | CS.acl | 2020-06-20 |
| 255 | Multimodal Quality Estimation For Machine Translation | SHU OKABE et. al. | We propose approaches to Quality Estimation (QE) for Machine Translation that explore both text and visual modalities for Multimodal QE. | CS.acl | 2020-06-20 |
| 256 | Conversational Word Embedding For Retrieval-Based Dialog System | WENTAO MA et. al. | In this paper, we propose a conversational word embedding method named PR-Embedding, which utilizes the conversation pairs {\textless}post, reply{\textgreater} to learn word embedding. | CS.acl | 2020-06-20 |
| 257 | Knowledge Distillation For Multilingual Unsupervised Neural Machine Translation | HAIPENG SUN et. al. | In this paper, we empirically introduce a simple method to translate between thirteen languages using a single encoder and a single decoder, making use of multilingual data to improve UNMT for all language pairs. | CS.acl | 2020-06-20 |
| 258 | Addressing Posterior Collapse With Mutual Information For Improved Variational Neural Machine Translation | ARYA D. MCCARTHY et. al. | This paper proposes a simple and effective approach to address the problem of posterior collapse in conditional variational autoencoders (CVAEs). | CS.acl | 2020-06-20 |
| 259 | A Study Of Non-autoregressive Model For Sequence Generation | YI REN et. al. | To quantify such dependency, we propose an analysis model called CoMMA to characterize the difficulty of different NAR sequence generation tasks. | CS.acl | 2020-06-20 |
| 260 | Speech Translation And The End-to-End Promise: Taking Stock Of Where We Are | MATTHIAS SPERBER et. al. | This paper provides a unifying categorization and nomenclature that covers both traditional and recent approaches and that may help researchers by highlighting both trade-offs and open research questions. | CS.acl | 2020-06-20 |
| 261 | Unsupervised Multimodal Neural Machine Translation With Pseudo Visual Pivoting | PO-YAO HUANG et. al. | In this paper, we investigate how to utilize visual content for disambiguation and promoting latent space alignment in unsupervised MMT. | CS.acl | 2020-06-20 |
| 262 | It’s Easier To Translate Out Of English Than Into It: Measuring Neural Translation Difficulty By Cross-Mutual Information | EMANUELE BUGLIARELLO et. al. | In this paper, we propose cross-mutual information (XMI): an asymmetric information-theoretic metric of machine translation difficulty that exploits the probabilistic nature of most neural machine translation models. | CS.acl | 2020-06-20 |
| 263 | Learning A Multi-Domain Curriculum For Neural Machine Translation | WEI WANG et. al. | This is achieved by carefully introducing instance-level domain-relevance features and automatically constructing a training curriculum to gradually concentrate on multi-domain relevant and noise-reduced data batches. | CS.acl | 2020-06-20 |
| 264 | On The Evaluation Of Machine Translation SystemsTrained With Back-Translation | SERGEY EDUNOV et. al. | In this work, we show that this conjecture is not empirically supported and that back-translation improves translation quality of both naturally occurring text as well as translationese according to professional human translators. | CS.acl | 2020-06-20 |
| 265 | Heterogeneous Graph Transformer For Graph-to-Sequence Learning | SHAOWEI YAO et. al. | In this paper, we propose the Heterogeneous Graph Transformer to independently model the different relations in the individual subgraphs of the original graph, including direct relations, indirect relations and multiple possible relations between nodes. | CS.acl | 2020-06-20 |
| 266 | Unsupervised Domain Clusters In Pretrained Language Models | ROEE AHARONI et. al. | We harness this property and propose domain data selection methods based on such models, which require only a small set of in-domain monolingual data. | CS.acl | 2020-06-20 |
| 267 | Modeling Word Formation In English–German Neural Machine Translation | MARION WELLER-DI MARCO et. al. | This paper studies strategies to model word formation in NMT using rich linguistic information, namely a word segmentation approach that goes beyond splitting into substrings by considering fusional morphology. | CS.acl | 2020-06-20 |
| 268 | Jointly Masked Sequence-to-Sequence Model For Non-Autoregressive Neural Machine Translation | JUNLIANG GUO et. al. | In this work, we introduce a jointly masked sequence-to-sequence model and explore its application on non-autoregressive neural machine translation{\textasciitilde}(NAT). | CS.acl | 2020-06-20 |
| 269 | Evaluating Robustness To Input Perturbations For Neural Machine Translation | XING NIU et. al. | This paper proposes additional metrics which measure the relative degradation and changes in translation when small perturbations are added to the input. | CS.acl | 2020-06-20 |
| 270 | Multimodal Transformer For Multimodal Machine Translation | SHAOWEI YAO et. al. | In this paper, we introduce the multimodal self-attention in Transformer to solve the issues above in MMT. | CS.acl | 2020-06-20 |
| 271 | Gender In Danger? Evaluating Speech Translation Technology On The MuST-SHE Corpus | LUISA BENTIVOGLI et. al. | We present the first thorough investigation of gender bias in speech translation, contributing with: i) the release of a benchmark useful for future studies, and ii) the comparison of different technologies (cascade and end-to-end) on two language directions (English-Italian/French). | CS.acl | 2020-06-20 |
| 272 | “You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases | DIRK HOVY et. al. | We show that as a consequence, the output of three commercial machine translation systems (Bing, DeepL, Google) make demographically diverse samples from five languages sound older and more male than the original. | CS.acl | 2020-06-20 |
| 273 | In Neural Machine Translation, What Does Transfer Learning Transfer? | ALHAM FIKRI AJI et. al. | We perform several ablation studies that limit information transfer, then measure the quality impact across three language pairs to gain a black-box understanding of transfer learning. | CS.acl | 2020-06-20 |
| 274 | How Does Selective Mechanism Improve Self-Attention Networks? | XINWEI GENG et. al. | In this paper, we bridge the gap by assessing the strengths of selective SANs (SSANs), which are implemented with a flexible and universal Gumbel-Softmax. | CS.acl | 2020-06-20 |
| 275 | Simple And Effective Retrieve-Edit-Rerank Text Generation | NABIL HOSSAIN et. al. | We propose to extend this framework with a simple and effective post-generation ranking approach. | CS.acl | 2020-06-20 |
| 276 | Improving Massively Multilingual Neural Machine Translation And Zero-Shot Translation | BIAO ZHANG et. al. | We argue that multilingual NMT requires stronger modeling capacity to support language pairs with varying typological characteristics, and overcome this bottleneck via language-specific components and deepening NMT architectures. | CS.acl | 2020-06-20 |
| 277 | Hard-Coded Gaussian Attention For Neural Machine Translation | WEIQIU YOU et. al. | We push further in this direction by developing a �hard-coded� attention variant without any learned parameters. | CS.acl | 2020-06-20 |
| 278 | Document Translation Vs. Query Translation For Cross-Lingual Information Retrieval In The Medical Domain | SHADI SALEH et. al. | We present a thorough comparison of two principal approaches to Cross-Lingual Information Retrieval: document translation (DT) and query translation (QT). | CS.acl | 2020-06-20 |
| 279 | Uncertainty-Aware Curriculum Learning For Neural Machine Translation | YIKAI ZHOU et. al. | We propose uncertainty-aware curriculum learning, which is motivated by the intuition that: 1) the higher the uncertainty in a translation pair, the more complex and rarer the information it contains; and 2) the end of the decline in model uncertainty indicates the completeness of current training stage. | CS.acl | 2020-06-20 |
| 280 | Does Multi-Encoder Help? A Case Study On Context-Aware Neural Machine Translation | BEI LI et. al. | In this paper, we investigate multi-encoder approaches in document-level neural machine translation (NMT). | CS.acl | 2020-06-20 |
| 281 | Translationese As A Language In “Multilingual” NMT | PARKER RILEY et. al. | Motivated by this, we model translationese and original (i.e. natural) text as separate languages in a multilingual model, and pose the question: can we perform zero-shot translation between original source text and original target text? | CS.acl | 2020-06-20 |
| 282 | Language-aware Interlingua For Multilingual Neural Machine Translation | CHANGFENG ZHU et. al. | In this paper, we incorporate a language-aware interlingua into the Encoder-Decoder architecture. | CS.acl | 2020-06-20 |
| 283 | Tangled Up In BLEU: Reevaluating The Evaluation Of Automatic Machine Translation Evaluation Metrics | NITIKA MATHUR et. al. | We show that current methods for judging metrics are highly sensitive to the translations used for assessment, particularly the presence of outliers, which often leads to falsely confident conclusions about a metric’s efficacy. | CS.acl | 2020-06-20 |
| 284 | Memory Transformer | MIKHAIL S. BURTSEV et. al. | In this work, we propose and study two extensions of the Transformer baseline (1) by adding memory tokens to store non-local representations, and (2) creating memory bottleneck for the global information. | CS.arxiv | 2020-06-20 |
| 285 | Multi-Domain Neural Machine Translation With Word-Level Adaptive Layer-wise Domain Mixing | HAOMING JIANG et. al. | To overcome this limitation, we propose a novel multi-domain NMT model using individual modules for each domain, on which we apply word-level, adaptive and layer-wise domain mixing. | CS.acl | 2020-06-20 |
| 286 | On The Inference Calibration Of Neural Machine Translation | SHUO WANG et. al. | By carefully designing experiments on three language pairs, our work provides in-depth analyses of the correlation between calibration and translation performance as well as linguistic properties of miscalibration and reports a number of interesting findings that might help humans better analyze, understand and improve NMT models. | CS.acl | 2020-06-20 |
| 287 | Leveraging Monolingual Data With Self-Supervision For Multilingual Neural Machine Translation | ADITYA SIDDHANT et. al. | In this work, we join these two lines of research and demonstrate the efficacy of monolingual data with self-supervision in multilingual NMT. | CS.acl | 2020-06-20 |
| 288 | Multi-Hypothesis Machine Translation Evaluation | MARINA FOMICHEVA et. al. | In this paper, we propose an alternative approach: instead of modelling linguistic variation in human reference we exploit the MT model uncertainty to generate multiple diverse translations and use these: (i) as surrogates to reference translations; (ii) to obtain a quantification of translation variability to either complement existing metric scores or (iii) replace references altogether. | CS.acl | 2020-06-20 |
| 289 | End-to-End Neural Word Alignment Outperforms GIZA++ | THOMAS ZENKEL et. al. | We present the first end-to-end neural word alignment method that consistently outperforms GIZA++ on three data sets. | CS.acl | 2020-06-20 |
| 290 | Lexically Constrained Neural Machine Translation With Levenshtein Transformer | RAYMOND HENDY SUSANTO et. al. | This paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation. | CS.acl | 2020-06-20 |
| 291 | Cross-Lingual Unsupervised Sentiment Classification With Multi-View Transfer Learning | HONGLIANG FEI et. al. | We propose an unsupervised cross-lingual sentiment classification model named multi-view encoder-classifier (MVEC) that leverages an unsupervised machine translation (UMT) system and a language discriminator. | CS.acl | 2020-06-20 |
| 292 | A Reinforced Generation Of Adversarial Examples For Neural Machine Translation | WEI ZOU et. al. | Instead of collecting and analyzing bad cases using limited handcrafted error features, here we investigate this issue by generating adversarial examples via a new paradigm based on reinforcement learning. | CS.acl | 2020-06-20 |
| 293 | Parallel Corpus Filtering Via Pre-trained Language Models | BOLIANG ZHANG et. al. | In this paper, we propose a novel approach to filter out noisy sentence pairs from web-crawled corpora via pre-trained language models. | CS.acl | 2020-06-20 |
| 294 | Character-Level Translation With Self-attention | YINGQIANG GAO et. al. | We explore the suitability of self-attention models for character-level neural machine translation. | CS.acl | 2020-06-20 |
| 295 | Learning To Recover From Multi-Modality Errors For Non-Autoregressive Neural Machine Translation | QIU RAN et. al. | To alleviate this problem, we propose a novel semi-autoregressive model RecoverSAT in this work, which generates a translation as a sequence of segments. | CS.acl | 2020-06-20 |
| 296 | ParaCrawl: Web-Scale Acquisition Of Parallel Corpora | MARTA BAÑÓN et. al. | We report on methods to create the largest publicly available parallel corpora by crawling the web, using open source software. | CS.acl | 2020-06-20 |
| 297 | BPE-Dropout: Simple And Effective Subword Regularization | IVAN PROVILKOV et. al. | We introduce BPE-dropout – simple and effective subword regularization method based on and compatible with conventional BPE. | CS.acl | 2020-06-20 |
| 298 | Automatic Machine Translation Evaluation Using Source Language Inputs And Cross-lingual Language Model | KOSUKE TAKAHASHI et. al. | We propose an automatic evaluation method of machine translation that uses source language sentences regarded as additional pseudo references. | CS.acl | 2020-06-20 |
| 299 | A Call For More Rigor In Unsupervised Cross-lingual Learning | MIKEL ARTETXE et. al. | We review motivations, definition, approaches, and methodology for unsupervised cross-lingual learning and call for a more rigorous position in each of them. | CS.acl | 2020-06-20 |
| 300 | Learning Aligned Embeddings For Semi-supervised Word Translation Using Maximum Mean Discrepancy | ANTONIO H. O. FONSECA et. al. | Here we propose an end-to-end approach for word embedding alignment that does not require known word pairs. | CS.arxiv | 2020-06-20 |
| 301 | Evaluating Explanation Methods For Neural Machine Translation | JIERUI LI et. al. | To this end, it proposes a principled metric based on fidelity in regard to the predictive behavior of the NMT model. | CS.acl | 2020-06-20 |
| 302 | SimulSpeech: End-to-End Simultaneous Speech To Text Translation | YI REN et. al. | In this work, we develop SimulSpeech, an end-to-end simultaneous speech to text translation system which translates speech in source language to text in target language concurrently. | CS.acl | 2020-06-20 |
| 303 | Phone Features Improve Speech Translation | ELIZABETH SALESKY et. al. | We compare cascaded and end-to-end models across high, medium, and low-resource conditions, and show that cascades remain stronger baselines. | CS.acl | 2020-06-20 |
| 304 | Improving Transformer Models By Reordering Their Sublayers | OFIR PRESS et. al. | We propose a new transformer pattern that adheres to this property, the sandwich transformer, and show that it improves perplexity on multiple word-level and character-level language modeling benchmarks, at no cost in parameters, memory, or training time. | CS.acl | 2020-06-20 |
| 305 | A Retrieve-and-Rewrite Initialization Method For Unsupervised Machine Translation | SHUO REN et. al. | In this paper, we propose a novel retrieval and rewriting based method to better initialize unsupervised translation models. | CS.acl | 2020-06-20 |
| 306 | Selecting Backtranslated Data From Multiple Sources For Improved Neural Machine Translation | XABIER SOTO et. al. | In this work we analyse the impact that data translated with rule-based, phrase-based statistical and neural MT systems has on new MT systems. | CS.acl | 2020-06-20 |
| 307 | Improving Neural Machine Translation With Soft Template Prediction | JIAN YANG et. al. | Inspired by the success of template-based and syntax-based approaches in other fields, we propose to use extracted templates from tree structures as soft target templates to guide the translation procedure. | CS.acl | 2020-06-20 |
| 308 | MLQA: Evaluating Cross-lingual Extractive Question Answering | PATRICK LEWIS et. al. | We present MLQA, a multi-way aligned extractive QA evaluation benchmark intended to spur research in this area. | CS.acl | 2020-06-20 |
| 309 | A Simple And Effective Unified Encoder For Document-Level Machine Translation | SHUMING MA et. al. | In this work, we propose a simple and effective unified encoder that can outperform the baseline models of dual-encoder models in terms of BLEU and METEOR scores. | CS.acl | 2020-06-20 |
| 310 | A Multi-Perspective Architecture For Semantic Code Search | RAJARSHI HALDAR et. al. | In this paper, we propose a novel multi-perspective cross-lingual neural framework for code-text matching, inspired in part by a previous model for monolingual text-to-text matching, to capture both global and local similarities. | CS.acl | 2020-06-20 |
| 311 | On The Limitations Of Cross-lingual Encoders As Exposed By Reference-Free Machine Translation Evaluation | WEI ZHAO et. al. | In this paper, we concern ourselves with reference-free machine translation (MT) evaluation where we directly compare source texts to (sometimes low-quality) system translations, which represents a natural adversarial setup for multilingual encoders. | CS.acl | 2020-06-20 |
| 312 | Content Word Aware Neural Machine Translation | KEHAI CHEN et. al. | To address this limitation, we first utilize word frequency information to distinguish between content and function words in a sentence, and then design a content word-aware NMT to improve translation performance. | CS.acl | 2020-06-20 |
| 313 | Using Context In Neural Machine Translation Training Objectives | DANIELLE SAUNDERS et. al. | We present Neural Machine Translation (NMT) training using document-level metrics with batch-level documents. | CS.acl | 2020-06-20 |
| 314 | Regularized Context Gates On Transformer For Machine Translation | XINTONG LI et. al. | This paper first provides a method to identify source and target contexts and then introduce a gate mechanism to control the source and target contributions in Transformer. In addition, to further reduce the bias problem in the gate mechanism, this paper proposes a regularization method to guide the learning of the gates with supervision automatically generated using pointwise mutual information. | CS.acl | 2020-06-20 |
| 315 | ENGINE: Energy-Based Inference Networks For Non-Autoregressive Machine Translation | LIFU TU et. al. | We propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model. | CS.acl | 2020-06-20 |
| 316 | Multiscale Collaborative Deep Models For Neural Machine Translation | XIANGPENG WEI et. al. | In this paper, we present a MultiScale Collaborative (MSC) framework to ease the training of NMT models that are substantially deeper than those used previously. | CS.acl | 2020-06-20 |
| 317 | Contextual Neural Machine Translation Improves Translation Of Cataphoric Pronouns | KAYYEN WONG et. al. | In this work, we investigate the effect of future sentences as context by comparing the performance of a contextual NMT model trained with the future context to the one trained with the past context. | CS.acl | 2020-06-20 |
| 318 | Norm-Based Curriculum Learning For Neural Machine Translation | XUEBO LIU et. al. | In this paper, we aim to improve the efficiency of training an NMT by introducing a novel norm-based curriculum learning method. | CS.acl | 2020-06-20 |
| 319 | Enhancing Machine Translation With Dependency-Aware Self-Attention | EMANUELE BUGLIARELLO et. al. | In this work, we investigate different approaches to incorporate syntactic knowledge in the Transformer model and also propose a novel, parameter-free, dependency-aware self-attention mechanism that improves its translation quality, especially for long sentences and in low-resource scenarios. | CS.acl | 2020-06-20 |
| 320 | A Mixture Of H – 1 Heads Is Better Than H Heads | HAO PENG et. al. | In this work, we instead reallocate them-the model learns to activate different heads on different inputs. | CS.acl | 2020-06-20 |
| 321 | Are We Estimating Or Guesstimating Translation Quality? | SHUO SUN et. al. | Our findings suggest that although QE models might capture fluency of translated sentences and complexity of source sentences, they cannot model adequacy of translations effectively. | CS.acl | 2020-06-20 |
| 322 | HAT: Hardware-Aware Transformers For Efficient Natural Language Processing | HANRUI WANG et. al. | To enable low-latency inference on resource-constrained hardware platforms, we propose to design Hardware-Aware Transformers (HAT) with neural architecture search. | CS.acl | 2020-06-20 |
| 323 | Parallel Sentence Mining By Constrained Decoding | PINZHEN CHEN et. al. | We present a novel method to extract parallel sentences from two monolingual corpora, using neural machine translation. | CS.acl | 2020-06-20 |
| 324 | Tagged Back-translation Revisited: Why Does It Really Work? | BENJAMIN MARIE et. al. | In this paper, we show that neural machine translation (NMT) systems trained on large back-translated data overfit some of the characteristics of machine-translated texts. | CS.acl | 2020-06-20 |
| 325 | BART: Denoising Sequence-to-Sequence Pre-training For Natural Language Generation, Translation, And Comprehension | MIKE LEWIS et. al. | We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. | CS.acl | 2020-06-20 |
| 326 | Self-Attention With Cross-Lingual Position Representation | LIANG DING et. al. | In this paper, we augment SANs with \textit{cross-lingual position representations} to model the bilingually aware latent structure for the input sentence. | CS.acl | 2020-06-20 |
| 327 | Variational Neural Machine Translation With Normalizing Flows | HENDRA SETIAWAN et. al. | In this paper, we propose to apply the VNMT framework to the state-of-the-art Transformer and introduce a more flexible approximate posterior based on normalizing flows. | CS.acl | 2020-06-20 |
| 328 | MMPE: A Multi-Modal Interface For Post-Editing Machine Translation | NICO HERBIG et. al. | Since this paradigm shift offers potential for modalities other than mouse and keyboard, we present MMPE, the first prototype to combine traditional input modes with pen, touch, and speech modalities for PE of MT. | CS.acl | 2020-06-20 |
| 329 | Deep Encoder, Shallow Decoder: Reevaluating The Speed-Quality Tradeoff In Machine Translation | JUNGO KASAI et. al. | In this work, we re-examine the trade-off and argue that transformer-based autoregressive models can be substantially sped up without loss in accuracy. | CS.arxiv | 2020-06-18 |
| 330 | Multi-branch Attentive Transformer | YANG FAN et. al. | In this work, we propose a simple yet effective variant of Transformer called multi-branch attentive Transformer (briefly, MAT), where the attention layer is the average of multiple branches and each branch is an independent multi-head attention layer. | CS.arxiv | 2020-06-18 |
| 331 | DBPal: A Fully Pluggable NL2SQL Training Pipeline | NATHANIEL WEIR et. al. | Based on these observations, we propose DBPal, a new approach that augments existing deep learning techniques in order to improve the performance of models for natural language to SQL translation. | CS.sigmod | 2020-06-17 |
| 332 | EPIE Dataset: A Corpus For Possible Idiomatic Expressions | PRATEEK SAXENA et. al. | With this in mind, we present our English Possible Idiomatic Expressions(EPIE) corpus containing 25206 sentences labelled with lexical instances of 717 idiomatic expressions. | CS.arxiv | 2020-06-16 |
| 333 | Cross-lingual Retrieval For Iterative Self-Supervised Training | CHAU TRAN et. al. | In this work, we found that the cross-lingual alignment can be further improved by training seq2seq models on sentence pairs mined using their own encoder outputs. | CS.arxiv | 2020-06-16 |
| 334 | Scalable Cross Lingual Pivots To Model Pronoun Gender For Translation | KELLIE WEBSTER et. al. | We propose a novel cross-lingual pivoting technique for automatically producing high-quality gender labels, and show that this data can be used to fine-tune a BERT classifier with 92% F1 for Spanish dropped feminine pronouns, compared with 30-51% for neural machine translation models and 54-71% for a non-fine-tuned BERT model. | CS.arxiv | 2020-06-15 |
| 335 | End-to-End Code Switching Language Models For Automatic Speech Recognition | AHAN M. R. et. al. | In this paper, we particularly work on the code-switched text, one of the most common occurrences in the bilingual communities across the world. | CS.arxiv | 2020-06-15 |
| 336 | Fine-grained Human Evaluation Of Transformer And Recurrent Approaches To Neural Machine Translation For English-to-Chinese | YUYING YE et. al. | This research presents a fine-grained human evaluation to compare the Transformer and recurrent approaches to neural machine translation (MT), on the translation direction English-to-Chinese. | CS.arxiv | 2020-06-15 |
| 337 | DynE: Dynamic Ensemble Decoding For Multi-Document Summarization | CHRIS HOKAMP et. al. | In this work we propose a simple decoding methodology which ensembles the output of multiple instances of the same model on different inputs. | CS.arxiv | 2020-06-15 |
| 338 | Sparse And Continuous Attention Mechanisms | ANDRÉ F. T. MARTINS et. al. | Sparse And Continuous Attention Mechanisms | CS.arxiv | 2020-06-12 |
| 339 | Video Understanding As Machine Translation | BRUNO KORBAR et. al. | In this work we remove the need for negative sampling by taking a generative modeling approach that poses the objective as a translation problem between modalities. | CS.arxiv | 2020-06-12 |
| 340 | Gender In Danger? Evaluating Speech Translation Technology On The MuST-SHE Corpus | LUISA BENTIVOGLI et. al. | We present the first thorough investigation of gender bias in speech translation, contributing with: i) the release of a benchmark useful for future studies, and ii) the comparison of different technologies (cascade and end-to-end) on two language directions (English-Italian/French). | CS.arxiv | 2020-06-10 |
| 341 | What’s The Difference Between Professional Human And Machine Translation? A Blind Multi-language Study On Domain-specific MT | LUKAS FISCHER et. al. | We find that the post-editing effort for MT segments is only higher in two out of three language pairs, and that the number of segments with wrong terminology, omissions, and typographical problems is similar in HT. | CS.arxiv | 2020-06-08 |
| 342 | Sign Language Transformers: Joint End-to-End Sign Language Recognition And Translation | NECATI CIHAN CAMGOZ et. al. | We introduce a novel transformer based architecture that jointly learns Continuous Sign Language Recognition and Translation while being trainable in an end-to-end manner. | CS.cvpr | 2020-06-08 |
| 343 | Universal Vector Neural Machine Translation With Effective Attention | SATISH MYLAPORE et. al. | In this paper, we propose a singular model for Neural Machine Translation based on encoder-decoder models. | CS.arxiv | 2020-06-08 |
| 344 | Modeling Discourse Structure For Document-level Neural Machine Translation | JUNXUAN CHEN et. al. | In this paper, we propose to improve document-level NMT with the aid of discourse structure information. | CS.arxiv | 2020-06-08 |
| 345 | Semi-Supervised Learning For Few-Shot Image-to-Image Translation | YAXING WANG et. al. | In this work, we go one step further and reduce the amount of required labeled data also from the source domain during training. | CS.cvpr | 2020-06-08 |
| 346 | HausaMT V1.0: Towards English-Hausa Neural Machine Translation | ADEWALE AKINFADERIN | In this paper, we curated different datasets containing Hausa-English parallel corpus for our translation. | CS.arxiv | 2020-06-08 |
| 347 | CycleGT: Unsupervised Graph-to-Text And Text-to-Graph Generation Via Cycle Training | QIPENG GUO et. al. | We present CycleGT, an unsupervised training framework that can bootstrap from fully non-parallel graph and text datasets, iteratively back translate between the two forms, and use a novel pretraining strategy. | CS.arxiv | 2020-06-08 |
| 348 | Pre-training Polish Transformer-based Language Models At Scale | SŁAWOMIR DADAS et. al. | In this study, we present two language models for Polish based on the popular BERT architecture. | CS.arxiv | 2020-06-07 |
| 349 | Growing Together: Modeling Human Language Learning With N-Best Multi-Checkpoint Machine Translation | EL MOATEZ BILLAH NAGOUDI et. al. | We describe our submission to the 2020 Duolingo Shared Task on Simultaneous Translation And Paraphrase for Language Education (STAPLE) (Mayhew et al., 2020). | CS.arxiv | 2020-06-07 |
| 350 | NITS-VC System For VATEX Video Captioning Challenge 2020 | ALOK SINGH et. al. | In this paper, a system description of the framework used for VATEX-2020 video captioning challenge is presented. | CS.arxiv | 2020-06-07 |
| 351 | ELITR Non-Native Speech Translation At IWSLT 2020 | DOMINIK MACHÁČEK et. al. | We describe systems for offline ASR, real-time ASR, and our cascaded approach to offline SLT and real-time SLT. | CS.arxiv | 2020-06-05 |
| 352 | Unsupervised Translation Of Programming Languages | MARIE-ANNE LACHAUX et. al. | In this paper, we propose to leverage recent approaches in unsupervised machine translation to train a fully unsupervised neural transcompiler. | CS.arxiv | 2020-06-05 |
| 353 | MLE-guided Parameter Search For Task Loss Minimization In Neural Sequence Modeling | SEAN WELLECK et. al. | In this paper, we develop an alternative method based on random search in the parameter space that leverages access to the maximum likelihood gradient. | CS.arxiv | 2020-06-04 |
| 354 | Using Self-Training To Improve Back-Translation In Low Resource Neural Machine Translation | IDRIS ABDULMUMIN et. al. | This work proposes a self-training strategy where the output of the backward model is used to improve the model itself through the forward translation technique. | CS.arxiv | 2020-06-04 |
| 355 | M3P: Learning Universal Representations Via Multitask Multilingual Multimodal Pre-training | HAOYANG HUANG et. al. | This paper presents a Multitask Multilingual Multimodal Pre-trained model (M3P) that combines multilingual-monomodal pre-training and monolingual-multimodal pre-training into a unified framework via multitask learning and weight sharing. We also build a new Multilingual Image-Language Dataset (MILD) by collecting large amounts of (text-query, image, context) triplets in 8 languages from the logs of a commercial search engine | CS.arxiv | 2020-06-03 |
| 356 | Cross-model Back-translated Distillation For Unsupervised Machine Translation | XUAN-PHI NGUYEN et. al. | 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. | CS.arxiv | 2020-06-03 |
| 357 | Self-Training For End-to-End Speech Translation | JUAN PINO et. al. | Our approach is shown to be more effective than simply pre-training the encoder on the speech recognition task. | CS.arxiv | 2020-06-03 |
| 358 | Cascaded Text Generation With Markov Transformers | YUNTIAN DENG et. al. | This work proposes an autoregressive model with sub-linear parallel time generation. | CS.arxiv | 2020-06-01 |
| 359 | Is 42 The Answer To Everything In Subtitling-oriented Speech Translation? | ALINA KARAKANTA et. al. | In this work, we explore two methods for applying Speech Translation (ST) to subtitling: a) a direct end-to-end and b) a classical cascade approach. | CS.arxiv | 2020-06-01 |
| 360 | Online Versus Offline NMT Quality: An In-depth Analysis On English-German And German-English | MAHA ELBAYAD et. al. | We conduct in this work an evaluation study comparing offline and online neural machine translation architectures. | CS.arxiv | 2020-06-01 |
| 361 | A Sentiment Analysis Dataset For Code-Mixed Malayalam-English | BHARATHI RAJA CHAKRAVARTHI et. al. | This paper presents a new gold standard corpus for sentiment analysis of code-mixed text in Malayalam-English annotated by voluntary annotators. | CS.arxiv | 2020-05-30 |
| 362 | Data Augmentation For Learning Bilingual Word Embeddings With Unsupervised Machine Translation | SOSUKE NISHIKAWA et. al. | In this paper, we propose using a pseudo-parallel corpus generated by an unsupervised machine translation model to facilitate structural similarity of the two embedding spaces and improve the quality of BWEs in the mapping method. | CS.arxiv | 2020-05-30 |
| 363 | Dynamic Masking For Improved Stability In Spoken Language Translation | YUEKUN YAO et. al. | We show how this mask can be set dynamically, improving the latency-flicker trade-off without sacrificing translation quality. | CS.arxiv | 2020-05-30 |
| 364 | Design And Implementation Of A Virtual 3D Educational Environment To Improve Deaf Education | ABDELAZIZ LAKHFIF | The goal of the project is the development of a machine translation system from Arabic to Algerian Sign Language that can be used as educational tool for Deaf children in algerian primary schools. | CS.arxiv | 2020-05-29 |
| 365 | Neural Simultaneous Speech Translation Using Alignment-Based Chunking | PATRICK WILKEN et. al. | We propose a neural machine translation (NMT) model that makes dynamic decisions when to continue feeding on input or generate output words. | CS.arxiv | 2020-05-29 |
| 366 | Variational Neural Machine Translation With Normalizing Flows | HENDRA SETIAWAN et. al. | In this paper, we propose to apply the VNMT framework to the state-of-the-art Transformer and introduce a more flexible approximate posterior based on normalizing flows. | CS.arxiv | 2020-05-28 |
| 367 | MT-Adapted Datasheets For Datasets: Template And Repository | MARTA R. COSTA-JUSSÀ et. al. | In this report we are taking the standardized model proposed by Gebru et al. (2018) for documenting the popular machine translation datasets of the EuroParl (Koehn, 2005) and News-Commentary (Barrault et al., 2019). | CS.arxiv | 2020-05-27 |
| 368 | The Unreasonable Volatility Of Neural Machine Translation Models | MARZIEH FADAEE et. al. | We investigate the unexpected volatility of NMT models where the input is semantically and syntactically correct. | CS.arxiv | 2020-05-25 |
| 369 | A Review Of Sentiment Analysis Research In Arabic Language | OUMAIMA OUESLATI et. al. | In this paper, we carry out an in-depth qualitative study of the most important research works in this context by presenting limits and strengths of existing approaches. | CS.arxiv | 2020-05-25 |
| 370 | ON-TRAC Consortium For End-to-End And Simultaneous Speech Translation Challenge Tasks At IWSLT 2020 | MAHA ELBAYAD et. al. | We propose an algorithm to control the latency of the ASR+MT cascade and achieve a good latency-quality trade-off on both subtasks. | CS.arxiv | 2020-05-24 |
| 371 | Character-level Transformer-based Neural Machine Translation | NIKOLAY BANAR et. al. | In this paper, we discuss a novel, Transformer-based approach, that we compare, both in speed and in quality to the Transformer at subword and character levels, as well as previously developed character-level models. | CS.arxiv | 2020-05-22 |
| 372 | Simplify-then-Translate: Automatic Preprocessing For Black-Box Machine Translation | SNEHA MEHTA et. al. | In this work, we introduce a method to improve such systems via automatic pre-processing (APP) using sentence simplification. | CS.arxiv | 2020-05-22 |
| 373 | Unsupervised Quality Estimation For Neural Machine Translation | MARINA FOMICHEVA et. al. | As an alternative, we devise an unsupervised approach to QE where no training or access to additional resources besides the MT system itself is required. To evaluate our approach we collect the first dataset that enables work on both black-box and glass-box approaches to QE. | CS.arxiv | 2020-05-21 |
| 374 | Towards Finite-State Morphology Of Kurdish | SINA AHMADI et. al. | In this paper, as the first attempt of its kind, the morphology of the Kurdish language (Sorani dialect) is described from a computational point of view. | CS.arxiv | 2020-05-21 |
| 375 | MultiMWE: Building A Multi-lingual Multi-Word Expression (MWE) Parallel Corpora | LIFENG HAN et. al. | In this paper, we present multi-lingual and bilingual MWE corpora that we have extracted from root parallel corpora. | CS.arxiv | 2020-05-21 |
| 376 | Is MAP Decoding All You Need? The Inadequacy Of The Mode In Neural Machine Translation | BRYAN EIKEMA et. al. | In this work, we criticise NMT models probabilistically showing that stochastic samples following the model’s own generative story do reproduce various statistics of the training data well, but that it is beam search that strays from such statistics. | CS.arxiv | 2020-05-20 |
| 377 | Grammatical Gender Associations Outweigh Topical Gender Bias In Crosslinguistic Word Embeddings | KATHERINE MCCURDY et. al. | Recent research has demonstrated that vector space models of semantics can reflect undesirable biases in human culture. | CS.arxiv | 2020-05-18 |
| 378 | Efficient Wait-k Models For Simultaneous Machine Translation | MAHA ELBAYAD et. al. | Wait-k decoders offer a simple but efficient approach for this problem. | CS.arxiv | 2020-05-18 |
| 379 | NEJM-enzh: A Parallel Corpus For English-Chinese Translation In The Biomedical Domain | BOXIANG LIU et. al. | In this study, we develop an effective pipeline to acquire and process an English-Chinese parallel corpus, consisting of about 100,000 sentence pairs and 3,000,000 tokens on each side, from the New England Journal of Medicine (NEJM). | CS.arxiv | 2020-05-18 |
| 380 | Encodings Of Source Syntax: Similarities In NMT Representations Across Target Languages | TYLER A. CHANG et. al. | We train neural machine translation (NMT) models from English to six target languages, using NMT encoder representations to predict ancestor constituent labels of source language words. | CS.arxiv | 2020-05-17 |
| 381 | Dual Learning: Theoretical Study And An Algorithmic Extension | ZHIBING ZHAO et. al. | In this paper, we aim at understanding why and when dual learning works. | CS.arxiv | 2020-05-17 |
| 382 | A Mixture Of $h-1$ Heads Is Better Than $h$ Heads | HAO PENG et. al. | In this work, we instead reallocate them — the model learns to activate different heads on different inputs. | CS.arxiv | 2020-05-13 |
| 383 | Reassessing Claims Of Human Parity And Super-Human Performance In Machine Translation At WMT 2019 | ANTONIO TORAL | Reassessing Claims Of Human Parity And Super-Human Performance In Machine Translation At WMT 2019 | CS.arxiv | 2020-05-12 |
| 384 | Neural Polysynthetic Language Modelling | LANE SCHWARTZ et. al. | When we consider polysynthetic languages (those at the extreme of morphological complexity), approaches like stemming, lemmatization, or subword modelling may not suffice. | CS.arxiv | 2020-05-11 |
| 385 | Hierarchical Attention Transformer Architecture For Syntactic Spell Correction | ABHISHEK NIRANJAN et. al. | In this paper, we propose multi encoder-single decoder variation of conventional transformer. | CS.arxiv | 2020-05-11 |
| 386 | A Framework For Hierarchical Multilingual Machine Translation | ION MADRAZO AZPIAZU et. al. | In this paper, we present a hierarchical framework for building multilingual machine translation strategies that takes advantage of a typological language family tree for enabling transfer among similar languages while avoiding the negative effects that result from incorporating languages that are too different to each other. | CS.arxiv | 2020-05-11 |
| 387 | DiscreTalk: Text-to-Speech As A Machine Translation Problem | TOMOKI HAYASHI et. al. | This paper proposes a new end-to-end text-to-speech (E2E-TTS) model based on neural machine translation (NMT). | CS.arxiv | 2020-05-11 |
| 388 | Learning To Detect Unacceptable Machine Translations For Downstream Tasks | MENG ZHANG et. al. | In this work, we put machine translation in a cross-lingual pipeline and introduce downstream tasks to define task-specific acceptability of machine translations. | CS.arxiv | 2020-05-08 |
| 389 | JASS: Japanese-specific Sequence To Sequence Pre-training For Neural Machine Translation | ZHUOYUAN MAO et. al. | To this end, we propose JASS, Japanese-specific Sequence to Sequence, as a novel pre-training alternative to MASS for NMT involving Japanese as the source or target language. We will release our code, pre-trained models and bunsetsu annotated data as resources for researchers to use in their own NLP tasks. | CS.arxiv | 2020-05-07 |
| 390 | Synthesizer: Rethinking Self-Attention In Transformer Models | YI TAY et. al. | To this end, we propose \textsc{Synthesizer}, a model that learns synthetic attention weights without token-token interactions. | CS.arxiv | 2020-05-02 |
| 392 | Improving Non-autoregressive Neural Machine Translation With Monolingual Data | JIAWEI ZHOU et. al. | Under this framework, we leverage large monolingual corpora to improve the NAR model’s performance, with the goal of transferring the AR model’s generalization ability while preventing overfitting. | CS.arxiv | 2020-05-02 |
| 393 | Facilitating Access To Multilingual COVID-19 Information Via Neural Machine Translation | ANDY WAY et. al. | Facilitating Access To Multilingual COVID-19 Information Via Neural Machine Translation | CS.arxiv | 2020-05-01 |
| 394 | CohEval: Benchmarking Coherence Models | TASNIM MOHIUDDIN et. al. | In this paper, we propose to benchmark coherence models on a number of synthetic and downstream tasks. | CS.arxiv | 2020-04-30 |
| 395 | Capsule-Transformer For Neural Machine Translation | SUFENG DUAN et. al. | In this paper, we thus propose the capsule-Transformer, which extends the linear transformation into a more general capsule routing algorithm by taking SAN as a special case of capsule network. | CS.arxiv | 2020-04-30 |
| 396 | Data And Representation For Turkish Natural Language Inference | EMRAH BUDUR et. al. | In this paper, we offer a positive response for natural language inference (NLI) in Turkish. | CS.arxiv | 2020-04-30 |
| 397 | NUBIA: NeUral Based Interchangeability Assessor For Text Generation | HASSAN KANE et. al. | We present NUBIA, a methodology to build automatic evaluation metrics for text generation using only machine learning models as core components. | CS.arxiv | 2020-04-30 |
| 398 | Imitation Attacks And Defenses For Black-box Machine Translation Systems | ERIC WALLACE et. al. | To mitigate these vulnerabilities, we propose a defense that modifies translation outputs in order to misdirect the optimization of imitation models. | CS.arxiv | 2020-04-30 |
| 399 | Accurate Word Alignment Induction From Neural Machine Translation | YUN CHEN et. al. | In this paper, we show that attention weights do capture accurate word alignment, which could only be revealed if we choose the correct decoding step and layer to induce word alignment. | CS.arxiv | 2020-04-30 |
| 400 | Addressing Zero-Resource Domains Using Document-Level Context In Neural Machine Translation | DARIO STOJANOVSKI et. al. | We present two document-level Transformer models which are capable of using large context sizes and we compare these models against strong Transformer baselines. | CS.arxiv | 2020-04-30 |
| 401 | Language Model Prior For Low-Resource Neural Machine Translation | CHRISTOS BAZIOTIS et. al. | In this work, we propose a novel approach to incorporate a LM as prior in a neural translation model (TM). | CS.arxiv | 2020-04-30 |
| 402 | Bridging Linguistic Typology And Multilingual Machine Translation With Multi-View Language Representations | ARTURO ONCEVAY et. al. | We propose to fuse both views using singular vector canonical correlation analysis and study what kind of information is induced from each source. | CS.arxiv | 2020-04-30 |
| 403 | Character-Level Translation With Self-attention | YINGQIANG GAO et. al. | We explore the suitability of self-attention models for character-level neural machine translation. | CS.arxiv | 2020-04-30 |
| 404 | Semi-Supervised Text Simplification With Back-Translation And Asymmetric Denoising Autoencoders | YANBIN ZHAO et. al. | To tackle this problem, we propose asymmetric denoising methods for sentences with separate complexity. | CS.arxiv | 2020-04-30 |
| 405 | Recipes For Adapting Pre-trained Monolingual And Multilingual Models To Machine Translation | ASA COOPER STICKLAND et. al. | This paper investigates the benefits and drawbacks of freezing parameters, and adding new ones, when fine-tuning a pre-trained model on MT. We focus on 1) Fine-tuning a model trained only on English monolingual data, BART. | CS.arxiv | 2020-04-30 |
| 406 | Can Your Context-Aware MT System Pass The DiP Benchmark Tests? : Evaluation Benchmarks For Discourse Phenomena In Machine Translation | PRATHYUSHA JWALAPURAM et. al. | We introduce the first of their kind MT benchmark datasets that aim to track and hail improvements across four main discourse phenomena: anaphora, lexical consistency, coherence and readability, and discourse connective translation. | CS.arxiv | 2020-04-30 |
| 407 | Vocabulary Adaptation For Distant Domain Adaptation In Neural Machine Translation | SHOETSU SATO et. al. | In this study, aiming to solve these vocabulary mismatches in distant domain adaptation, we propose vocabulary adaptation, a simple method for effective fine-tuning that adapts embedding layers in a given pre-trained NMT model to the target domain. | CS.arxiv | 2020-04-30 |
| 408 | Towards Reasonably-Sized Character-Level Transformer NMT By Finetuning Subword Systems | JINDŘICH LIBOVICKÝ et. al. | We use only the vanilla 6-layer Transformer Base architecture. | CS.arxiv | 2020-04-29 |
| 409 | Syntax-aware Data Augmentation For Neural Machine Translation | SUFENG DUAN et. al. | In this paper, we propose a novel data augmentation enhancement strategy for neural machine translation. | CS.arxiv | 2020-04-29 |
| 410 | Adversarial Subword Regularization For Robust Neural Machine Translation | JUNGSOO PARK et. al. | In this paper, we present adversarial subword regularization (ADVSR) to study whether gradient signals during training can be a substitute criterion for exposing diverse subword segmentations. | CS.arxiv | 2020-04-29 |
| 411 | Automatic Machine Translation Evaluation In Many Languages Via Zero-Shot Paraphrasing | BRIAN THOMPSON et. al. | We propose the use of a sequence-to-sequence paraphraser for automatic machine translation evaluation. | CS.arxiv | 2020-04-29 |
| 412 | Simulated Multiple Reference Training Improves Low-Resource Machine Translation | HUDA KHAYRALLAH et. al. | We introduce Simulated Multiple Reference Training (SMRT), a novel MT training method that approximates the full space of possible translations by sampling a paraphrase of the reference sentence from a paraphraser and training the MT model to predict the paraphraser’s distribution over possible tokens. | CS.arxiv | 2020-04-29 |
| 413 | Automatically Identifying Gender Issues In Machine Translation Using Perturbations | HILA GONEN et. al. | We use our method to compile an evaluation benchmark spanning examples for four languages from three language families, which we publicly release to facilitate research. | CS.arxiv | 2020-04-29 |
| 414 | Learning Non-Monotonic Automatic Post-Editing Of Translations From Human Orderings | ANTÓNIO GÓIS et. al. | In this paper, we analyze the orderings produced by human post-editors and use them to train an automatic post-editing system. | CS.arxiv | 2020-04-29 |
| 415 | Scheduled DropHead: A Regularization Method For Transformer Models | WANGCHUNSHU ZHOU et. al. | In this paper, we introduce DropHead, a structured dropout method specifically designed for regularizing the multi-head attention mechanism, which is a key component of transformer, a state-of-the-art model for various NLP tasks. | CS.arxiv | 2020-04-28 |
| 416 | The Explanation Game: Towards Prediction Explainability Through Sparse Communication | MARCOS V. TREVISO et. al. | In this work, we provide a unified perspective of explainability as a communication problem between an explainer and a layperson about a classifier’s decision. | CS.arxiv | 2020-04-28 |
| 417 | Assessing The Bilingual Knowledge Learned By Neural Machine Translation Models | SHILIN HE et. al. | In this paper, we bridge the gap by assessing the bilingual knowledge learned by NMT models with phrase table — an interpretable table of bilingual lexicons. | CS.arxiv | 2020-04-27 |
| 418 | From Unsupervised Machine Translation To Adversarial Text Generation | A. RASHID et. al. | We present a self-attention based bilingual adversarial text generator (B-GAN) which can learn to generate text from the encoder representation of an unsupervised neural machine translation system. | CS.icassp | 2020-04-26 |
| 419 | Controllable Time-Delay Transformer For Real-Time Punctuation Prediction And Disfluency Detection | Q. CHEN et. al. | In this paper, we propose a Controllable Time-delay Transformer (CT-Transformer) model that jointly completes the punctuation prediction and disfluency detection tasks in real time. | CS.icassp | 2020-04-26 |
| 420 | Converting Written Language To Spoken Language With Neural Machine Translation For Language Modeling | S. ANDO et. al. | We address this problem by generating texts in spoken language from those in written language by using a neural machine translation (NMT) model. | CS.icassp | 2020-04-26 |
| 421 | End-end Speech-to-Text Translation With Modality Agnostic Meta-Learning | S. INDURTHI ET AL. | In this work, we adopt a meta-learning algorithm to train a modality agnostic multi-task model that transfers knowledge from source tasks=ASR+MT to target task=ST where the ST task severely lacks data. | CS.icassp | 2020-04-26 |
| 422 | Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates | J. IRANZO-S�NCHEZ ET AL. | In this paper we present Europarl-ST, a novel multilingual SLT corpus containing paired audio-text samples for SLT from and into 6 European languages, for a total of 30 different translation directions. | CS.icassp | 2020-04-26 |
| 423 | Clotho: An Audio Captioning Dataset | K. DROSSOS et. al. | In this paper we present Clotho, a dataset for audio captioning consisting of 4981 audio samples of 15 to 30 seconds duration and 24 905 captions of eight to 20 words length, and a baseline method to provide initial results. | CS.icassp | 2020-04-26 |
| 424 | Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation | N. ARIVAZHAGAN et. al. | We investigate the problem of simultaneous machine translation of long-form speech content. | CS.icassp | 2020-04-26 |
| 425 | End-to-End Speech Translation With Self-Contained Vocabulary Manipulation | M. TU et. al. | But vocabulary manipulation is hard to apply to the end-to-end speech-text translation, because neither source text nor speech-to-target mapping is available. We introduce a method that avoids this dependence. | CS.icassp | 2020-04-26 |
| 426 | Scalable Multilingual Frontend For TTS | A. CONKIE AND A. FINCH | This paper describes progress towards making a Neural Text-to-Speech (TTS) Frontend that works for many languages and can be easily extended to new languages. | CS.icassp | 2020-04-26 |
| 427 | T-GSA: Transformer With Gaussian-Weighted Self-Attention For Speech Enhancement | J. KIM et. al. | In this paper, we propose a Transformer with Gaussian-weighted self-attention (T-GSA), whose attention weights are attenuated according to the distance between target and context symbols. | CS.icassp | 2020-04-26 |
| 428 | ASR Error Correction And Domain Adaptation Using Machine Translation | A. MANI et. al. | We propose a simple technique to perform domain adaptation for ASR error correction via machine translation. | CS.icassp | 2020-04-26 |
| 429 | Neural Machine Translation With Monte-Carlo Tree Search | JERROD PARKER et. al. | The main idea of our project is to instead leverage Monte-Carlo Tree Search (MCTS) to search for good output words with guidance from a combined policy and value network architecture in a similar fashion as AlphaZero. | CS.arxiv | 2020-04-26 |
| 430 | Fixed-Point Optimization Of Transformer Neural Network | Y. BOO AND W. SUNG | In this study, we quantize the parameters and hidden signals of the Transformer for complexity reduction. | CS.icassp | 2020-04-26 |
| 431 | All Word Embeddings From One Embedding | SHO TAKASE et. al. | In this study, to reduce the total number of parameters, the embeddings for all words are represented by transforming a shared embedding. | CS.arxiv | 2020-04-25 |
| 432 | Jointly Trained Transformers Models For Spoken Language Translation | HARI KRISHNA VYDANA et. al. | In this work this degradation in the performance is reduced by creating an end to-end differentiable pipeline between the ASR and MT systems. | CS.arxiv | 2020-04-25 |
| 433 | On Sparsifying Encoder Outputs In Sequence-to-Sequence Models | BIAO ZHANG et. al. | In this work, by contrast, we hypothesize that these encoder outputs can be compressed to shorten the sequence delivered for decoding. | CS.arxiv | 2020-04-24 |
| 434 | Lite Transformer With Long-Short Range Attention | ZHANGHAO WU et. al. | In this paper, we present an efficient mobile NLP architecture, Lite Transformer to facilitate deploying mobile NLP applications on edge devices. | CS.arxiv | 2020-04-24 |
| 435 | Practical Comparable Data Collection For Low-Resource Languages Via Images | AMAN MADAAN et. al. | We propose a method of curating high-quality comparable training data for low-resource languages with monolingual annotators. | CS.arxiv | 2020-04-24 |
| 436 | Multiple Segmentations Of Thai Sentences For Neural Machine Translation | ALBERTO PONCELAS et. al. | In this work, we explore how to augment a set of English–Thai parallel data by replicating sentence-pairs with different word segmentation methods on Thai, as training data for NMT model training. | CS.arxiv | 2020-04-23 |
| 437 | Correct Me If You Can: Learning From Error Corrections And Markings | JULIA KREUTZER et. al. | We present the first user study on annotation cost and machine learnability for the less popular annotation mode of error markings. | CS.arxiv | 2020-04-23 |
| 438 | When And Why Is Unsupervised Neural Machine Translation Useless? | YUNSU KIM et. al. | This paper studies the practicality of the current state-of-the-art unsupervised methods in neural machine translation (NMT). | CS.arxiv | 2020-04-22 |
| 439 | Discretized Bottleneck In VAE: Posterior-Collapse-Free Sequence-to-Sequence Learning | YANG ZHAO et. al. | In this paper, we propose a principled approach to eliminate this issue by applying a discretized bottleneck in the latent space. | CS.arxiv | 2020-04-22 |
| 440 | Syntactic Structure From Deep Learning | TAL LINZEN et. al. | In this article, we survey representative studies of the syntactic abilities of deep networks, and discuss the broader implications that this work has for theoretical linguistics. | CS.arxiv | 2020-04-22 |
| 441 | Testing Machine Translation Via Referential Transparency | PINJIA HE et. al. | To address this problem, we introduce referentially transparent inputs (RTIs), a simple, widely applicable methodology for validating machine translation software. | CS.arxiv | 2020-04-21 |
| 442 | Attention Is Not Only A Weight: Analyzing Transformers With Vector Norms | GORO KOBAYASHI et. al. | This paper shows that attention weights alone are only one of the two factors that determine the output of attention and proposes a norm-based analysis that incorporates the second factor, the norm of the transformed input vectors. | CS.arxiv | 2020-04-21 |
| 443 | ESPnet-ST: All-in-One Speech Translation Toolkit | HIROFUMI INAGUMA et. al. | We present ESPnet-ST, which is designed for the quick development of speech-to-speech translation systems in a single framework. | CS.arxiv | 2020-04-21 |
| 444 | Learnings From Technological Interventions In A Low Resource Language: A Case-Study On Gondi | DEVANSH MEHTA et. al. | In this paper, we report the adoption and deployment of 4 technology-driven methods of data collection for Gondi, a low-resource vulnerable language spoken by around 2.3 million tribal people in south and central India. | CS.arxiv | 2020-04-21 |
| 445 | PHINC: A Parallel Hinglish Social Media Code-Mixed Corpus For Machine Translation | VIVEK SRIVASTAVA et. al. | This paper presents a parallel corpus of the 13,738 code-mixed English-Hindi sentences and their corresponding translation in English. We are releasing the parallel corpus to facilitate future research opportunities in code-mixed machine translation. | CS.arxiv | 2020-04-20 |
| 446 | SimAlign: High Quality Word Alignments Without Parallel Training Data Using Static And Contextualized Embeddings | MASOUD JALILI SABET et. al. | We propose word alignment methods that require no parallel data. | CS.arxiv | 2020-04-18 |
| 447 | Generative Adversarial Networks For Video-to-Video Domain Adaptation | JIAWEI CHEN et. al. | In this work, we propose a novel generative adversarial network (GAN), namely VideoGAN, to transfer the video-based data across different domains. | CS.arxiv | 2020-04-17 |
| 448 | Enriching The Transformer With Linguistic And Semantic Factors For Low-Resource Machine Translation | JORDI ARMENGOL-ESTAPÉ et. al. | This study proposes enhancing the current state-of-the-art neural machine translation architecture, the Transformer, so that it allows to introduce external knowledge. | CS.arxiv | 2020-04-16 |
| 449 | Building A Multi-domain Neural Machine Translation Model Using Knowledge Distillation | IDRISS MGHABBAR et. al. | In this paper, we propose a new training pipeline where knowledge distillation and multiple specialized teachers allow us to efficiently finetune a model without adding new costs at inference time. | CS.arxiv | 2020-04-15 |
| 450 | Non-Autoregressive Machine Translation With Latent Alignments | CHITWAN SAHARIA et. al. | This paper investigates two latent alignment models for non-autoregressive machine translation, namely CTC and Imputer. | CS.arxiv | 2020-04-15 |
| 451 | Multilingual Machine Translation: Closing The Gap Between Shared And Language-specific Encoder-Decoders | CARLOS ESCOLANO et. al. | In this paper, we propose an alternative approach that is based on language-specific encoder-decoders, and can thus be more easily extended to new languages by learning their corresponding modules. | CS.arxiv | 2020-04-14 |
| 452 | Balancing Training For Multilingual Neural Machine Translation | XINYI WANG et. al. | In this paper, we propose a method that instead automatically learns how to weight training data through a data scorer that is optimized to maximize performance on all test languages. | CS.arxiv | 2020-04-14 |
| 453 | BLEU Might Be Guilty But References Are Not Innocent | MARKUS FREITAG et. al. | We study different methods to collect references and compare their value in automated evaluation by reporting correlation with human evaluation for a variety of systems and metrics. | CS.arxiv | 2020-04-13 |
| 454 | Neural Machine Translation: Challenges, Progress And Future | JIAJUN ZHANG et. al. | Nowadays, neural machine translation (NMT) which models direct mapping between source and target languages with deep neural networks has achieved a big breakthrough in translation performance and become the de facto paradigm of MT. This article makes a review of NMT framework, discusses the challenges in NMT, introduces some exciting recent progresses and finally looks forward to some potential future research trends. | CS.arxiv | 2020-04-13 |
| 455 | Reinforced Curriculum Learning On Pre-trained Neural Machine Translation Models | MINGJUN ZHAO et. al. | In this paper, we aim to learn a curriculum for improving a pre-trained NMT model by re-selecting influential data samples from the original training set and formulate this task as a reinforcement learning problem. | CS.arxiv | 2020-04-12 |
| 456 | When Does Unsupervised Machine Translation Work? | KELLY MARCHISIO et. al. | We find that performance rapidly deteriorates when source and target corpora are from different domains, and that random word embedding initialization can dramatically affect downstream translation performance. | CS.arxiv | 2020-04-11 |
| 457 | LAReQA: Language-agnostic Answer Retrieval From A Multilingual Pool | UMA ROY et. al. | We present LAReQA, a challenging new benchmark for language-agnostic answer retrieval from a multilingual candidate pool. | CS.arxiv | 2020-04-11 |
| 458 | Style-transfer And Paraphrase: Looking For A Sensible Semantic Similarity Metric | IVAN YAMSHCHIKOV et. al. | This paper provides a comprehensive analysis for more than a dozen of such methods. | CS.arxiv | 2020-04-10 |
| 459 | Scalable Multilingual Frontend For TTS | ALISTAIR CONKIE et. al. | This paper describes progress towards making a Neural Text-to-Speech (TTS) Frontend that works for many languages and can be easily extended to new languages. | CS.arxiv | 2020-04-10 |
| 460 | An In-depth Walkthrough On Evolution Of Neural Machine Translation | ROHAN JAGTAP et. al. | This paper aims to study the major trends in Neural Machine Translation, the state of the art models in the domain and a high level comparison between them. | CS.arxiv | 2020-04-10 |
| 461 | Translation Artifacts In Cross-lingual Transfer Learning | MIKEL ARTETXE et. al. | In this paper, we show that such translation process can introduce subtle artifacts that have a notable impact in existing cross-lingual models. | CS.arxiv | 2020-04-09 |
| 462 | Self-Training For Unsupervised Neural Machine Translation In Unbalanced Training Data Scenarios | HAIPENG SUN et. al. | Based on this scenario, we propose UNMT self-training mechanisms to train a robust UNMT system and improve its performance in this case. | CS.arxiv | 2020-04-09 |
| 463 | Reducing Gender Bias In Neural Machine Translation As A Domain Adaptation Problem | DANIELLE SAUNDERS et. al. | During inference we propose a lattice-rescoring scheme which outperforms all systems evaluated in Stanovsky et al (2019) on WinoMT with no degradation of general test set BLEU, and we show this scheme can be applied to remove gender bias in the output of `black box` online commercial MT systems. | CS.arxiv | 2020-04-09 |
| 464 | On Optimal Transformer Depth For Low-Resource Language Translation | ELAN VAN BILJON et. al. | In this work, we find that the current trend in the field to use very large models is detrimental for low-resource languages, since it makes training more difficult and hurts overall performance, confirming previous observations. | CS.arxiv | 2020-04-09 |
| 465 | Explicit Reordering For Neural Machine Translation | KEHAI CHEN et. al. | Thus, we propose a novel reordering method to explicitly model this reordering information for the Transformer-based NMT. | CS.arxiv | 2020-04-08 |
| 466 | Transfer Learning And Subword Sampling For Asymmetric-resource One-to-many Neural Translation | STIG-ARNE GRÖNROOS et. al. | We review these approaches in the context of an asymmetric-resource one-to-many translation task, in which the pair of target languages are related, with one being a very low-resource and the other a higher-resource language. | CS.arxiv | 2020-04-08 |
| 467 | Cross-lingual Emotion Intensity Prediction | IREAN NAVAS ALEJO et. al. | Consequently, we explore cross-lingual transfer approaches for fine-grained emotion detection in Spanish and Catalan tweets. To this end we annotate a test set of Spanish and Catalan tweets using Best-Worst scaling. | CS.arxiv | 2020-04-08 |
| 468 | Learning To Scale Multilingual Representations For Vision-Language Tasks | ANDREA BURNS et. al. | In this paper, we propose a Scalable Multilingual Aligned Language Representation (SMALR) that supports many languages with few model parameters without sacrificing downstream task performance. | CS.arxiv | 2020-04-08 |
| 469 | Re-translation Versus Streaming For Simultaneous Translation | NAVEEN ARIVAZHAGAN et. al. | We study a related problem in which revisions to the hypothesis beyond strictly appending words are permitted. | CS.arxiv | 2020-04-07 |
| 470 | Improving Fluency Of Non-Autoregressive Machine Translation | ZDENĚK KASNER et. al. | We train models for three language pairs: German, Czech, and Romanian from and into English. | CS.arxiv | 2020-04-07 |
| 471 | Graph-to-Tree Neural Networks For Learning Structured Input-Output Translation With Applications To Semantic Parsing And Math Word Problem | SHUCHENG LI et. al. | In this paper, we present a novel Graph-to-Tree Neural Networks, namely Graph2Tree consisting of a graph encoder and a hierarchical tree decoder, that encodes an augmented graph-structured input and decodes a tree-structured output. | CS.arxiv | 2020-04-07 |
| 472 | Dynamic Data Selection And Weighting For Iterative Back-Translation | ZI-YI DOU et. al. | In this paper, we provide insights into this commonly used approach and generalize it to a dynamic curriculum learning strategy, which is applied to iterative back-translation models. | CS.arxiv | 2020-04-07 |
| 473 | Self-Induced Curriculum Learning In Self-Supervised Neural Machine Translation | DANA RUITER et. al. | In this study, we provide an in-depth analysis of the sampling choices the SSNMT model makes during training. | CS.arxiv | 2020-04-07 |
| 474 | Towards Multimodal Simultaneous Neural Machine Translation | AIZHAN IMANKULOVA et. al. | To alleviate this shortage, we propose multimodal simultaneous neural machine translation (MSNMT), which leverages visual information as an additional modality. | CS.arxiv | 2020-04-07 |
| 475 | Machine Translation With Unsupervised Length-Constraints | JAN NIEHUES | In this paper, we explore one of these, the generation of constraint translation. | CS.arxiv | 2020-04-07 |
| 476 | Human Motion Transfer From Poses In The Wild | JIAN REN et. al. | In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. To further boost research on the topic, we build two human motion datasets. | CS.arxiv | 2020-04-07 |
| 477 | Cross-lingual Supervision Improves Unsupervised Neural Machine Translation | MINGXUAN WANG et. al. | In this work, we introduce a multilingual unsupervised NMT (\method) framework to leverage weakly supervised signals from high-resource language pairs to zero-resource translation directions. | CS.arxiv | 2020-04-07 |
| 478 | Meta-Learning For Few-Shot NMT Adaptation | AMR SHARAF et. al. | We present META-MT, a meta-learning approach to adapt Neural Machine Translation (NMT) systems in a few-shot setting. | CS.arxiv | 2020-04-06 |
| 479 | Dictionary-based Data Augmentation For Cross-Domain Neural Machine Translation | WEI PENG et. al. | This paper proposes a dictionary-based data augmentation (DDA) method for cross-domain NMT. | CS.arxiv | 2020-04-06 |
| 480 | Bootstrapping A Crosslingual Semantic Parser | TOM SHERBORNE et. al. | We develop a Transformer-based parser combining paraphrases by ensembling attention over multiple encoders and present new versions of ATIS and Overnight in German and Chinese for evaluation. | CS.arxiv | 2020-04-06 |
| 481 | Applying Cyclical Learning Rate To Neural Machine Translation | CHOON MENG LEE et. al. | Drawing inspiration from the successful application of cyclical learning rate policy for computer vision related convolutional networks and datasets, we explore how cyclical learning rate can be applied to train transformer-based neural networks for neural machine translation. | CS.arxiv | 2020-04-06 |
| 482 | Finding The Optimal Vocabulary Size For Neural Machine Translation | THAMME GOWDA et. al. | We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. | CS.arxiv | 2020-04-05 |
| 483 | AR: Auto-Repair The Synthetic Data For Neural Machine Translation | SHANBO CHENG et. al. | In this paper, we propose a novel Auto- Repair (AR) framework to improve the quality of synthetic data. | CS.arxiv | 2020-04-05 |
| 484 | Understanding Learning Dynamics For Neural Machine Translation | CONGHUI ZHU et. al. | In this paper we propose to understand learning dynamics of NMT by using a recent proposed technique named Loss Change Allocation (LCA)~\citep{lan-2019-loss-change-allocation}. | CS.arxiv | 2020-04-05 |
| 485 | Detecting And Understanding Generalization Barriers For Neural Machine Translation | GUANLIN LI et. al. | Based on the modified one, we propose three simple methods for barrier detection by the search-aware risk estimation through counterfactual generation. | CS.arxiv | 2020-04-05 |
| 486 | Reference Language Based Unsupervised Neural Machine Translation | ZUCHAO LI et. al. | Experimental results show that our methods improve the quality of UNMT over that of a strong baseline that uses only one auxiliary language, demonstrating the usefulness of the proposed reference language-based UNMT and establishing a good start for the community. | CS.arxiv | 2020-04-05 |
| 487 | Conversational Question Reformulation Via Sequence-to-Sequence Architectures And Pretrained Language Models | SHENG-CHIEH LIN et. al. | This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs). | CS.arxiv | 2020-04-04 |
| 488 | Incorporating Bilingual Dictionaries For Low Resource Semi-Supervised Neural Machine Translation | SREYASHI NAG et. al. | We propose a simple data augmentation technique to address both this shortcoming. | CS.arxiv | 2020-04-04 |
| 489 | Machine Translation Pre-training For Data-to-Text Generation — A Case Study In Czech | MIHIR KALE et. al. | In this paper, we study the effectiveness of machine translation based pre-training for data-to-text generation in non-English languages. | CS.arxiv | 2020-04-04 |
| 490 | Learning Synchronous Context-free Grammars With Multiple Specialised Non-terminals For Hierarchical Phrase-based Translation | FELIPE SÁNCHEZ-MARTÍNEZ et. al. | This paper presents a method to learn synchronous context-free grammars with a huge number of initial non-terminals, which are then grouped via a clustering algorithm. | CS.arxiv | 2020-04-03 |
| 491 | A Set Of Recommendations For Assessing Human-Machine Parity In Language Translation | SAMUEL LÄUBLI et. al. | We show that the professional human translations contained significantly fewer errors, and that perceived quality in human evaluation depends on the choice of raters, the availability of linguistic context, and the creation of reference translations. | CS.arxiv | 2020-04-03 |
| 492 | Editable Neural Networks | ANTON SINITSIN et. al. | In this work, we investigate the problem of neural network editing $-$ how one can efficiently patch a mistake of the model on a particular sample, without influencing the model behavior on other samples. | CS.arxiv | 2020-04-01 |
| 493 | Igbo-English Machine Translation: An Evaluation Benchmark | IGNATIUS EZEANI et. al. | In this work, we discuss our effort toward building a standard machine translation benchmark dataset for Igbo, one of the 3 major Nigerian languages. | CS.arxiv | 2020-04-01 |
| 494 | Assessing Human Translations From French To Bambara For Machine Learning: A Pilot Study | MICHAEL LEVENTHAL et. al. | We present novel methods for assessing the quality of human-translated aligned texts for learning machine translation models of under-resourced languages. | CS.arxiv | 2020-03-31 |
| 495 | On The Integration Of LinguisticFeatures Into Statistical And Neural Machine Translation | EVA VANMASSENHOVE | We cover a series of problems related to the integration of specific linguistic features into statistical and neural MT, aiming to analyse and provide a solution to some of them. | CS.arxiv | 2020-03-31 |
| 496 | Low Resource Neural Machine Translation: A Benchmark For Five African Languages | SURAFEL M. LAKEW et. al. | In this work, we benchmark NMT between English and five African LRL pairs (Swahili, Amharic, Tigrigna, Oromo, Somali [SATOS]). | CS.arxiv | 2020-03-31 |
| 497 | Evaluating Amharic Machine Translation | ASMELASH TEKA HADGU et. al. | In this paper, we develop and share a dataset to automatically evaluate the quality of MT systems for Amharic. | CS.arxiv | 2020-03-31 |
| 498 | Learning Contextualized Sentence Representations For Document-Level Neural Machine Translation | PEI ZHANG et. al. | In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence. | CS.arxiv | 2020-03-29 |
| 499 | Towards Supervised And Unsupervised Neural Machine Translation Baselines For Nigerian Pidgin | OREVAOGHENE AHIA et. al. | This work aims to establish supervised and unsupervised neural machine translation (NMT) baselines between English and Nigerian Pidgin. | CS.arxiv | 2020-03-27 |
| 500 | FFR V1.0: Fon-French Neural Machine Translation | BONAVENTURE F. P. DOSSOU et. al. | In this paper, we describe our pilot project: the creation of a large growing corpora for Fon-to-French translations and our FFR v1.0 model, trained on this dataset. | CS.arxiv | 2020-03-26 |
| 501 | Towards Neural Machine Translation For Edoid Languages | IRORO ORIFE | Using the new JW300 public dataset, we trained and evaluated baseline translation models for four widely spoken languages in this group: \`Ed\’o, \’Es\’an, Urhobo and Isoko. | CS.arxiv | 2020-03-24 |
| 502 | Felix: Flexible Text Editing Through Tagging And Insertion | JONATHAN MALLINSON et. al. | We present Felix — a flexible text-editing approach for generation, designed to derive the maximum benefit from the ideas of decoding with bi-directional contexts and self-supervised pre-training. | CS.arxiv | 2020-03-24 |
| 503 | SAC: Accelerating And Structuring Self-Attention Via Sparse Adaptive Connection | XIAOYA LI et. al. | In this paper, we present a method for accelerating and structuring self-attentions: Sparse Adaptive Connection (SAC). | CS.arxiv | 2020-03-22 |
| 504 | Analyzing Word Translation Of Transformer Layers | HONGFEI XU et. al. | In this paper, we propose approaches to analyze the translation performed in encoder / decoder layers of the Transformer. | CS.arxiv | 2020-03-21 |
| 505 | A Joint Approach To Compound Splitting And Idiomatic Compound Detection | IRINA KROTOVA et. al. | We develop a two-fold deep learning-based approach of noun compound splitting and idiomatic compound detection for the German language that we train using a newly collected corpus of annotated German compounds. | CS.arxiv | 2020-03-21 |
| 506 | Language Technology Programme For Icelandic 2019-2023 | ANNA BJÖRK NIKULÁSDÓTTIR et. al. | In this paper, we describe a new national language technology programme for Icelandic. | CS.arxiv | 2020-03-20 |
| 507 | Utilizing Language Relatedness To Improve Machine Translation: A Case Study On Languages Of The Indian Subcontinent | ANOOP KUNCHUKUTTAN et. al. | In this work, we present an extensive study of statistical machine translation involving languages of the Indian subcontinent. | CS.arxiv | 2020-03-19 |
| 508 | Unsupervised Pidgin Text Generation By Pivoting English Data And Self-Training | ERNIE CHANG et. al. | In this work, we develop techniques targeted at bridging the gap between Pidgin English and English in the context of natural language generation. | CS.arxiv | 2020-03-18 |
| 509 | Multi-modal Dense Video Captioning | VLADIMIR IASHIN et. al. | In this paper, we present a new dense video captioning approach that is able to utilize any number of modalities for event description. | CS.arxiv | 2020-03-17 |
| 510 | TRANS-BLSTM: Transformer With Bidirectional LSTM For Language Understanding | ZHIHENG HUANG et. al. | In this paper, we investigate how these two modeling techniques can be combined to create a more powerful model architecture. | CS.arxiv | 2020-03-15 |
| 511 | Investigating Entity Knowledge In BERT With Simple Neural End-To-End Entity Linking | SAMUEL BROSCHEIT | In this study we investigate the following questions: (a) Can all those steps be learned jointly with a model for contextualized text-representations, i.e. BERT (Devlin et al., 2019)? | CS.arxiv | 2020-03-11 |
| 512 | Capturing Document Context Inside Sentence-level Neural Machine Translation Models With Self-training | ELMAN MANSIMOV et. al. | We propose an approach that doesn’t require training a specialized model on parallel document-level corpora and is applied to a trained sentence-level NMT model at decoding time. | CS.arxiv | 2020-03-11 |
| 513 | Investigating The Decoders Of Maximum Likelihood Sequence Models: A Look-ahead Approach | YU-SIANG WANG et. al. | We propose a k-step look-ahead module to consider the likelihood information of a rollout up to k steps. | CS.arxiv | 2020-03-07 |
| 514 | Morfessor EM+Prune: Improved Subword Segmentation With Expectation Maximization And Pruning | STIG-ARNE GRÖNROOS et. al. | In this paper, we discuss and compare training algorithms for a unigram subword model, based on the Expectation Maximization algorithm and lexicon pruning. | CS.arxiv | 2020-03-06 |
| 515 | Quality Of Word Embeddings On Sentiment Analysis Tasks | ERION ÇANO et. al. | In this study we compare performance of a dozen of pretrained word embedding models on lyrics sentiment analysis and movie review polarity tasks. | CS.arxiv | 2020-03-06 |
| 516 | An Empirical Accuracy Law For Sequential Machine Translation: The Case Of Google Translate | LUCAS NUNES SEQUEIRA et. al. | In this research, we have established, through empirical testing, a law that relates the number of translating hops to translation accuracy in sequential machine translation in Google Translate. | CS.arxiv | 2020-03-05 |
| 517 | Distill, Adapt, Distill: Training Small, In-Domain Models For Neural Machine Translation | MITCHELL A. GORDON et. al. | We explore best practices for training small, memory efficient machine translation models with sequence-level knowledge distillation in the domain adaptation setting. | CS.arxiv | 2020-03-05 |
| 518 | Evaluating Low-Resource Machine Translation Between Chinese And Vietnamese With Back-Translation | HONGZHENG LI et. al. | In this paper, we investigate the impacts of BT on Asia language translations between the extremely low-resource Chinese and Vietnamese language pair. | CS.arxiv | 2020-03-04 |
| 519 | Meta-Embeddings Based On Self-Attention | QICHEN LI et. al. | In this paper, we devise a new meta-embedding model based on the self-attention mechanism, namely the Duo. | CS.arxiv | 2020-03-03 |
| 520 | Controllable Time-Delay Transformer For Real-Time Punctuation Prediction And Disfluency Detection | QIAN CHEN et. al. | In this paper, we propose a Controllable Time-delay Transformer (CT-Transformer) model that jointly completes the punctuation prediction and disfluency detection tasks in real time. | CS.arxiv | 2020-03-02 |
| 521 | Towards Automatic Face-to-Face Translation | PRAJWAL K R et. al. | In light of the recent breakthroughs in automatic machine translation systems, we propose a novel approach that we term as Face-to-Face Translation. | CS.arxiv | 2020-03-01 |
| 522 | Soft-Root-Sign Activation Function | YUAN ZHOU et. al. | To this end, we introduce a novel activation function to manage to overcome the above three challenges. | CS.arxiv | 2020-03-01 |
| 523 | A Finite State Transducer Based Morphological Analyzer Of Maithili Language | RAZA RAHI et. al. | In this paper, we present a finite state transducer based inflectional morphological analyzer for a resource poor language of India, known as Maithili. | CS.arxiv | 2020-02-29 |
| 524 | Fast Indexes For Gapped Pattern Matching | MANUEL CÁCERES et. al. | We describe indexes for searching large data sets for variable-length-gapped (VLG) patterns. | CS.arxiv | 2020-02-28 |
| 525 | Do All Roads Lead To Rome? Understanding The Role Of Initialization In Iterative Back-Translation | MIKEL ARTETXE et. al. | In this paper, we analyze the role that such initialization plays in iterative back-translation. | CS.arxiv | 2020-02-28 |
| 526 | Modeling Future Cost For Neural Machine Translation | CHAOQUN DUAN et. al. | To respond to this issue, we propose a simple and effective method to model the future cost of each target word for NMT systems. | CS.arxiv | 2020-02-28 |
| 527 | Robust Unsupervised Neural Machine Translation With Adversarial Training | HAIPENG SUN et. al. | Robust Unsupervised Neural Machine Translation With Adversarial Training | CS.arxiv | 2020-02-28 |
| 528 | Echo State Neural Machine Translation | ANKUSH GARG et. al. | We present neural machine translation (NMT) models inspired by echo state network (ESN), named Echo State NMT (ESNMT), in which the encoder and decoder layer weights are randomly generated then fixed throughout training. | CS.arxiv | 2020-02-26 |
| 529 | Marathi To English Neural Machine Translation With Near Perfect Corpus And Transformers | SWAPNIL ASHOK JADHAV | In this exercise, we trained and compared variety of Neural Machine Marathi to English Translators trained with BERT-tokenizer by huggingface and various Transformer based architectures using Facebook’s Fairseq platform with limited but almost correct parallel corpus to achieve better BLEU scores than Google on Tatoeba and Wikimedia open datasets. | CS.arxiv | 2020-02-26 |
| 530 | MuST-Cinema: A Speech-to-Subtitles Corpus | ALINA KARAKANTA et. al. | In this work, we present MuST-Cinema, a multilingual speech translation corpus built from TED subtitles. | CS.arxiv | 2020-02-25 |
| 531 | Fixed Encoder Self-Attention Patterns In Transformer-Based Machine Translation | ALESSANDRO RAGANATO et. al. | In this paper, we propose to replace all but one attention head of each encoder layer with simple fixed — non-learnable — attentive patterns that are solely based on position and do not require any external knowledge. | CS.arxiv | 2020-02-24 |
| 532 | GRET: Global Representation Enhanced Transformer | RONGXIANG WENG et. al. | In this paper, we propose a novel global representation enhanced Transformer (GRET) to explicitly model global representation in the Transformer network. | CS.arxiv | 2020-02-24 |
| 533 | Machine Translation System Selection From Bandit Feedback | JASON NARADOWSKY et. al. | In this work we take a different approach, treating the problem of adaptation as one of selection. | CS.arxiv | 2020-02-22 |
| 534 | Accessing Higher-level Representations In Sequential Transformers With Feedback Memory | ANGELA FAN et. al. | In this work, we propose the Feedback Transformer architecture that exposes all previous representations to all future representations, meaning the lowest representation of the current timestep is formed from the highest-level abstract representation of the past. | CS.arxiv | 2020-02-21 |
| 535 | Guider L’attention Dans Les Modeles De Sequence A Sequence Pour La Prediction Des Actes De Dialogue | PIERRE COLOMBO et. al. | In this work, we introduce a seq2seq model tailored for DA classification using: a hierarchical encoder, a novel guided attention mechanism and beam search applied to both training and inference. | CS.arxiv | 2020-02-21 |
| 536 | Modelling Latent Skills For Multitask Language Generation | KRIS CAO et. al. | We present a generative model for multitask conditional language generation. | CS.arxiv | 2020-02-21 |
| 537 | Guiding Attention In Sequence-to-sequence Models For Dialogue Act Prediction | PIERRE COLOMBO et. al. | In this work, we introduce a seq2seq model tailored for DA classification using: a hierarchical encoder, a novel guided attention mechanism and beam search applied to both training and inference. | CS.arxiv | 2020-02-20 |
| 538 | Balancing Cost And Benefit With Tied-Multi Transformers | RAJ DABRE et. al. | We propose and evaluate a novel procedure for training multiple Transformers with tied parameters which compresses multiple models into one enabling the dynamic choice of the number of encoder and decoder layers during decoding. | CS.arxiv | 2020-02-20 |
| 539 | A Survey Of Deep Learning Techniques For Neural Machine Translation | SHUOHENG YANG et. al. | A Survey Of Deep Learning Techniques For Neural Machine Translation | CS.arxiv | 2020-02-18 |
| 540 | Towards Making The Most Of Context In Neural Machine Translation | ZAIXIANG ZHENG et. al. | We argue that previous research did not make a clear use of the global context, and propose a new document-level NMT framework that deliberately models the local context of each sentence with the awareness of the global context of the document in both source and target languages. | CS.arxiv | 2020-02-18 |
| 541 | Incorporating BERT Into Neural Machine Translation | JINHUA ZHU et. al. | We conduct experiments on supervised (including sentence-level and document-level translations), semi-supervised and unsupervised machine translation, and achieve state-of-the-art results on seven benchmark datasets. | CS.arxiv | 2020-02-17 |
| 542 | On The Discrepancy Between Density Estimation And Sequence Generation | JASON LEE et. al. | In this paper, by comparing several density estimators on five machine translation tasks, we find that the correlation between rankings of models based on log-likelihood and BLEU varies significantly depending on the range of the model families being compared. | CS.arxiv | 2020-02-17 |
| 543 | Controlling Computation Versus Quality For Neural Sequence Models | ANKUR BAPNA et. al. | In this work, we utilize conditional computation to make neural sequence models (Transformer) more efficient and computation-aware during inference. | CS.arxiv | 2020-02-17 |
| 544 | Multi-layer Representation Fusion For Neural Machine Translation | QIANG WANG et. al. | In this paper, we propose a multi-layer representation fusion (MLRF) approach to fusing stacked layers. | CS.arxiv | 2020-02-16 |
| 545 | Neural Machine Translation With Joint Representation | YANYANG LI et. al. | In this paper, we employ Joint Representation that fully accounts for each possible interaction. | CS.arxiv | 2020-02-16 |
| 546 | Deep Learning For Source Code Modeling And Generation: Models, Applications And Challenges | TRIET H. M. LE et. al. | After that, we introduce recent DL mechanisms suitable to solve such problems. | CS.arxiv | 2020-02-13 |
| 547 | Validating Uncertainty In Medical Image Translation | JACOB C. REINHOLD et. al. | In this work, we investigate using dropout to estimate epistemic and aleatoric uncertainty in a CT-to-MR image translation task. | CS.arxiv | 2020-02-11 |
| 548 | Learning Coupled Policies For Simultaneous Machine Translation | PHILIP ARTHUR et. al. | We present an imitation learning (IL) approach to efficiently learn effective coupled programmer-interpreter policies. | CS.arxiv | 2020-02-11 |
| 549 | A Probabilistic Formulation Of Unsupervised Text Style Transfer | JUNXIAN HE et. al. | We present a deep generative model for unsupervised text style transfer that unifies previously proposed non-generative techniques. | CS.arxiv | 2020-02-10 |
| 550 | Explainable Deep RDFS Reasoner | BASSEM MAKNI et. al. | To achieve explainability in RDFS reasoning, we revisit this approach and introduce a new neural network model that gets the input graph–as a sequence of graph words– as well as the encoding of the inferred triple and outputs the derivation for the inferred triple. | CS.arxiv | 2020-02-09 |
| 551 | MetaMT, A Meta Learning Method Leveraging Multiple Domain Data For Low Resource Machine Translation | RUMENG LI et. al. | In this paper, we present a novel NMT model with a new word embedding transition technique for fast domain adaption. | CS.aaai | 2020-02-07 |
| 552 | Sequence Generation With Optimal-Transport-Enhanced Reinforcement Learning | LIQUN CHEN et. al. | We propose a principled approach to address the difficulties associated with RL-based solutions, namely, high-variance gradients, uninformative rewards and brittle training. | CS.aaai | 2020-02-07 |
| 553 | A Dataset For Low-Resource Stylized Sequence-to-Sequence Generation | YU WU et. al. | We provide three baselines, the pivot-based method, the teacher-student method, and the back-translation method. We construct two large-scale, multiple-reference datasets for low-resource stylized S2S, the Machine Translation Formality Corpus (MTFC) that is easy to evaluate and the Twitter Conversation Formality Corpus (TCFC) that tackles an important problem in chatbots. | CS.aaai | 2020-02-07 |
| 554 | Cross-Lingual Pre-Training Based Transfer For Zero-Shot Neural Machine Translation | BAIJUN JI et. al. | To this end, we introduce one monolingual pre-training method and two bilingual pre-training methods to obtain a universal encoder for different languages. | CS.aaai | 2020-02-07 |
| 555 | Explicit Sentence Compression For Neural Machine Translation | ZUCHAO LI et. al. | In this paper, we propose an explicit sentence compression method to enhance the source sentence representation for NMT. | CS.aaai | 2020-02-07 |
| 556 | Modeling Fluency And Faithfulness For Diverse Neural Machine Translation | YANG FENG et. al. | To address the problem of teacher forcing, we propose a method to introduce an evaluation module to guide the distribution of the prediction. | CS.aaai | 2020-02-07 |
| 557 | MaskGEC: Improving Neural Grammatical Error Correction Via Dynamic Masking | ZEWEI ZHAO et. al. | In this paper, we propose a simple yet effective method to improve the NMT-based GEC models by dynamic masking. | CS.aaai | 2020-02-07 |
| 558 | Towards Making The Most Of BERT In Neural Machine Translation | JIACHENG YANG et. al. | In this work, we introduce a concerted training framework (CTnmt) that is the key to integrate the pre-trained LMs to neural machine translation (NMT). | CS.aaai | 2020-02-07 |
| 559 | Stochastic Loss Function | QINGLIANG LIU et. al. | To improve learning efficiency, we develop Stochastic Loss Function (SLF) to dynamically and automatically generating appropriate gradients to train deep networks in the same round of back-propagation, while maintaining the completeness and differentiability of the training pipeline. | CS.aaai | 2020-02-07 |
| 560 | Latent-Variable Non-Autoregressive Neural Machine Translation With Deterministic Inference Using A Delta Posterior | RAPHAEL SHU et. al. | Inspired by recent refinement-based approaches, we propose LaNMT, a latent-variable non-autoregressive model with continuous latent variables and deterministic inference procedure. | CS.aaai | 2020-02-07 |
| 561 | Visual Agreement Regularized Training For Multi-Modal Machine Translation | PENGCHENG YANG et. al. | To make better use of visual information, this work presents visual agreement regularized training. | CS.aaai | 2020-02-07 |
| 562 | Go From The General To The Particular: Multi-Domain Translation With Domain Transformation Networks | YONG WANG et. al. | Previous work shows that the standard neural machine translation (NMT) model, trained on mixed-domain data, generally captures the general knowledge, but misses the domain-specific knowledge. | CS.aaai | 2020-02-07 |
| 563 | Unsupervised Neural Dialect Translation With Commonality And Diversity Modeling | YU WAN et. al. | In this paper, we investigate how to exploit the commonality and diversity between dialects thus to build unsupervised translation models merely accessing to monolingual data. In order to examine the effectiveness of the proposed models, we collect 20 million monolingual corpus for each of Mandarin and Cantonese, which are official language and the most widely used dialect in China. | CS.aaai | 2020-02-07 |
| 564 | Controlling Neural Machine Translation Formality With Synthetic Supervision | XING NIU et. al. | This work aims to produce translations that convey source language content at a formality level that is appropriate for a particular audience. | CS.aaai | 2020-02-07 |
| 565 | Simplify-Then-Translate: Automatic Preprocessing For Black-Box Translation | SNEHA MEHTA et. al. | In this work, we introduce a method to improve such systems via automatic pre-processing (APP) using sentence simplification. | CS.aaai | 2020-02-07 |
| 566 | Graph Transformer For Graph-to-Sequence Learning | DENG CAI et. al. | Unlike graph neural networks that restrict the information exchange between immediate neighborhood, we propose a new model, known as Graph Transformer, that uses explicit relation encoding and allows direct communication between two distant nodes. | CS.aaai | 2020-02-07 |
| 567 | MULE: Multimodal Universal Language Embedding | DONGHYUN KIM et. al. | In this paper, we present a modular approach which can easily be incorporated into existing vision-language methods in order to support many languages. | CS.aaai | 2020-02-07 |
| 568 | IntroVNMT: An Introspective Model For Variational Neural Machine Translation | XIN SHENG et. al. | We propose a novel introspective model for variational neural machine translation (IntroVNMT) in this paper, inspired by the recent successful application of introspective variational autoencoder (IntroVAE) in high quality image synthesis. | CS.aaai | 2020-02-07 |
| 569 | Evaluating The Cross-Lingual Effectiveness Of Massively Multilingual Neural Machine Translation | ADITYA SIDDHANT et. al. | In this paper, we evaluate the cross-lingual effectiveness of representations from the encoder of a massively multilingual NMT model on 5 downstream classification and sequence labeling tasks covering a diverse set of over 50 languages. | CS.aaai | 2020-02-07 |
| 570 | Neuron Interaction Based Representation Composition For Neural Machine Translation | JIAN LI et. al. | Starting from this intuition, we propose a novel approach to compose representations learned by different components in neural machine translation (e.g., multi-layer networks or multi-head attention), based on modeling strong interactions among neurons in the representation vectors. | CS.aaai | 2020-02-07 |
| 571 | Alternating Language Modeling For Cross-Lingual Pre-Training | JIAN YANG et. al. | In this work, we introduce a novel cross-lingual pre-training method, called Alternating Language Modeling (ALM). | CS.aaai | 2020-02-07 |
| 572 | Monolingual Transfer Learning Via Bilingual Translators For Style-Sensitive Paraphrase Generation | TOMOYUKI KAJIWARA et. al. | We tackle the low-resource problem in style transfer by employing transfer learning that utilizes abundantly available raw corpora. | CS.aaai | 2020-02-07 |
| 573 | Fine-Tuning By Curriculum Learning For Non-Autoregressive Neural Machine Translation | JUNLIANG GUO et. al. | In this work, we introduce curriculum learning into fine-tuning for NAT. | CS.aaai | 2020-02-07 |
| 574 | Acquiring Knowledge From Pre-Trained Model To Neural Machine Translation | RONGXIANG WENG et. al. | In this paper, we propose an Apt framework for acquiring knowledge from pre-trained model to NMT. | CS.aaai | 2020-02-07 |
| 575 | Effective Modeling Of Encoder-Decoder Architecture For Joint Entity And Relation Extraction | TAPAS NAYAK et. al. | In this paper, we propose two approaches to use encoder-decoder architecture for jointly extracting entities and relations. | CS.aaai | 2020-02-07 |
| 576 | Improving Context-Aware Neural Machine Translation Using Self-Attentive Sentence Embedding | HYEONGU YUN et. al. | In this paper, we propose Hierarchical Context Encoder (HCE) that is able to exploit multiple context sentences separately using the hierarchical FAN structure. | CS.aaai | 2020-02-07 |
| 577 | Balancing Quality And Human Involvement: An Effective Approach To Interactive Neural Machine Translation | TIANXIANG ZHAO et. al. | In response to these pitfalls, we propose a novel interactive NMT model, which explicitly accounts the history of human involvements and particularly is optimized towards two objectives corresponding to the translation quality and the cost of human involvement, respectively. | CS.aaai | 2020-02-07 |
| 578 | A Multilingual View Of Unsupervised Machine Translation | XAVIER GARCIA et. al. | We present a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation. | CS.arxiv | 2020-02-07 |
| 579 | Transductive Ensemble Learning For Neural Machine Translation | YIREN WANG et. al. | In this paper, we study how to effectively aggregate multiple NMT models under the transductive setting where the source sentences of the test set are known. | CS.aaai | 2020-02-07 |
| 580 | Generating Diverse Translation By Manipulating Multi-Head Attention | ZEWEI SUN et. al. | In this paper, we report an interesting phenomenon in its encoder-decoder multi-head attention: different attention heads of the final decoder layer align to different word translation candidates. | CS.aaai | 2020-02-07 |
| 581 | Neural Machine Translation With Byte-Level Subwords | CHANGHAN WANG et. al. | In this paper, we investigate byte-level subwords, specifically byte-level BPE (BBPE), which is compacter than character vocabulary and has no out-of-vocabulary tokens, but is more efficient than using pure bytes only is. | CS.aaai | 2020-02-07 |
| 582 | Translating Web Search Queries Into Natural Language Questions | ADARSH KUMAR et. al. | In this paper, we are proposing a method to generate well-formed natural language question from a given keyword-based query, which has the same question intent as the query. | CS.arxiv | 2020-02-07 |
| 583 | Learning To Transfer: Unsupervised Domain Translation Via Meta-Learning | JIANXIN LIN et. al. | In this work, we take on unsupervised domain translation problems from a meta-learning perspective. | CS.aaai | 2020-02-07 |
| 584 | Minimizing The Bag-of-Ngrams Difference For Non-Autoregressive Neural Machine Translation | CHENZE SHAO et. al. | In this paper, we propose to train NAT to minimize the Bag-of-Ngrams (BoN) difference between the model output and the reference sentence. | CS.aaai | 2020-02-07 |
| 585 | PMIndia — A Collection Of Parallel Corpora Of Languages Of India | BARRY HADDOW et. al. | In this paper, we described a new publicly available corpus (PMIndia) consisting of parallel sentences which pair 13 major languages of India with English. | CS.arxiv | 2020-01-27 |
| 586 | Semi-Autoregressive Training Improves Mask-Predict Decoding | MARJAN GHAZVININEJAD et. al. | We introduce a new training method for conditional masked language models, SMART, which mimics the semi-autoregressive behavior of mask-predict, producing training examples that contain model predictions as part of their inputs. | CS.arxiv | 2020-01-23 |
| 587 | Pre-training Via Leveraging Assisting Languages And Data Selection For Neural Machine Translation | HAIYUE SONG et. al. | To this end, we propose to exploit monolingual corpora of other languages to complement the scarcity of monolingual corpora for the LOI. | CS.arxiv | 2020-01-22 |
| 588 | A Simple Baseline To Semi-Supervised Domain Adaptation For Machine Translation | DI JIN et. al. | In this work, we propose a simple but effect approach to the semi-supervised domain adaptation scenario of NMT, where the aim is to improve the performance of a translation model on the target domain consisting of only non-parallel data with the help of supervised source domain data. | CS.arxiv | 2020-01-22 |
| 589 | Normalization Of Input-output Shared Embeddings In Text Generation Models | JINYANG LIU et. al. | Based on linear algebra and statistical theories, this paper locates the shortcoming of existed input-output embedding weight sharing method, then raises methods for improving input-output weight shared embedding, among which methods of normalization of embedding weight matrices show best performance. | CS.arxiv | 2020-01-22 |
| 590 | Multilingual Denoising Pre-training For Neural Machine Translation | YINHAN LIU et. al. | We present mBART — a sequence-to-sequence denoising auto-encoder pre-trained on large-scale monolingual corpora in many languages using the BART objective. | CS.arxiv | 2020-01-22 |
| 591 | From Speech-to-Speech Translation To Automatic Dubbing | MARCELLO FEDERICO et. al. | We present enhancements to a speech-to-speech translation pipeline in order to perform automatic dubbing. | CS.arxiv | 2020-01-19 |
| 592 | Non-Autoregressive Machine Translation With Disentangled Context Transformer | JUNGO KASAI et. al. | We propose an attention-masking based model, called Disentangled Context (DisCo) transformer, that simultaneously generates all tokens given different contexts. | CS.arxiv | 2020-01-15 |
| 593 | Bi-Decoder Augmented Network For Neural Machine Translation | BOYUAN PAN et. al. | To alleviate this problem, in this paper, we propose a novel Bi-Decoder Augmented Network (BiDAN) for the neural machine translation task. | CS.arxiv | 2020-01-13 |
| 594 | Machine Learning Approaches For Amharic Parts-of-speech Tagging | IBRAHIM GASHAW et. al. | The aim of this work is to improve POS tagging performance for the Amharic language, which was never above 91%. | CS.arxiv | 2020-01-10 |
| 595 | Learning To Multi-Task Learn For Better Neural Machine Translation | POORYA ZAREMOODI et. al. | We propose a novel framework for learning the training schedule, ie learning to multi-task learn, for the MTL setting of interest. | CS.arxiv | 2020-01-09 |
| 596 | Exploring Benefits Of Transfer Learning In Neural Machine Translation | TOM KOCMI | For the former scenario, we present a proof-of-concept method by reusing a model trained by other researchers. | CS.arxiv | 2020-01-06 |
| 597 | A Comprehensive Survey Of Multilingual Neural Machine Translation | RAJ DABRE et. al. | In this paper, we present an in-depth survey of existing literature on MNMT. | CS.arxiv | 2020-01-04 |
| 598 | Learning Accurate Integer Transformer Machine-Translation Models | EPHREM WU | We describe a method for training accurate Transformer machine-translation models to run inference using 8-bit integer (INT8) hardware matrix multipliers, as opposed to the more costly single-precision floating-point (FP32) hardware. | CS.arxiv | 2020-01-03 |
| 599 | Towards Optimal Transport With Global Invariances | DAVID ALVAREZ-MELIS et. al. | In this work, we propose a general framework for optimal transport in the presence of latent global transformations. | CS.aistats | 2019-12-30 |
| 600 | Densely Connected Graph Convolutional Networks For Graph-to-Sequence Learning | ZHIJIANG GUO et. al. | Unlike various existing approaches where shallow architectures were used for capturing local structural information only, we introduce a dense connection strategy, proposing a novel Densely Connected Graph Convolutional Network (DCGCN). | CS.tacl | 2019-12-30 |
| 601 | Attention-Passing Models For Robust And Data-Efficient End-to-End Speech Translation | MATTHIAS SPERBER et. al. | In this paper, we demonstrate that direct speech translation models require more data to perform well than cascaded models, and although they allow including auxiliary data through multi-task training, they are poor at exploiting such data, putting them at a severe disadvantage. | CS.tacl | 2019-12-30 |
| 602 | Synchronous Bidirectional Neural Machine Translation | LONG ZHOU et. al. | In this paper, we introduce a synchronous bidirectional-neural machine translation (SB-NMT) that predicts its outputs using left-to-right and right-to-left decoding simultaneously and interactively, in order to leverage both of the history and future information at the same time. | CS.tacl | 2019-12-30 |
| 603 | Semantic Neural Machine Translation Using AMR | LINFENG SONG et. al. | In this work, we study the usefulness of AMR (abstract meaning representation) on NMT. | CS.tacl | 2019-12-30 |
| 604 | Learning Neural Sequence-to-Sequence Models From Weak Feedback With Bipolar Ramp Loss | LAURA JEHL et. al. | We present several objectives for two separate weakly supervised tasks, machine translation and semantic parsing. | CS.tacl | 2019-12-30 |
| 605 | Encoding Word Order In Complex Embeddings | BENYOU WANG et. al. | We present a novel and principled solution for modeling both the global absolute positions of words and their order relationships. | CS.arxiv | 2019-12-27 |
| 606 | A Study Of Multilingual Neural Machine Translation | XU TAN et. al. | This paper concentrates on a deep understanding of multilingual NMT and conducts a comprehensive study on a multilingual dataset with more than 20 languages. | CS.arxiv | 2019-12-25 |
| 607 | Coursera Corpus Mining And Multistage Fine-Tuning For Improving Lectures Translation | HAIYUE SONG et. al. | To address this, we examine a language independent framework for parallel corpus mining which is a quick and effective way to mine a parallel corpus from publicly available lectures at Coursera. | CS.arxiv | 2019-12-25 |
| 608 | Tag-less Back-Translation | IDRIS ABDULMUMIN et. al. | This work presents pre-training and fine-tuning as a simplified but more effective approach of differentiating between the two data. | CS.arxiv | 2019-12-22 |
| 609 | Compositional Continual Language Learning | YUANPENG LI et. al. | Inspired by that, in this paper, we propose a method for compositional continual learning of sequence-to-sequence models. | CS.iclr | 2019-12-21 |
| 610 | Editable Neural Networks | ANTON SINITSIN et. al. | Training neural networks so you can efficiently patch them later. | CS.iclr | 2019-12-21 |
| 611 | BERTScore: Evaluating Text Generation With BERT | TIANYI ZHANG* et. al. | We propose BERTScore, an automatic evaluation metric for text generation, which correlates better with human judgments and provides stronger model selection performance than existing metrics. | CS.iclr | 2019-12-21 |
| 612 | Reducing Transformer Depth On Demand With Structured Dropout | ANGELA FAN et. al. | Layerdrop, a form of structured dropout that allows you to train one model at training time and prune to any desired depth at test time. You can also | CS.iclr | 2019-12-21 |
| 613 | Monotonic Multihead Attention | XUTAI MA et. al. | Make the transformer streamable with monotonic attention. | CS.iclr | 2019-12-21 |
| 614 | Efficient Transformer For Mobile Applications | ZHANGHAO WU* et. al. | In this paper, we investigate the mobile setting (under 500M Mult-Adds) for NLP tasks to facilitate the deployment on the edge devices. | CS.iclr | 2019-12-21 |
| 615 | Tree-Structured Attention With Hierarchical Accumulation | XUAN-PHI NGUYEN et. al. | In this paper, we attempt to bridge this gap with Hierarchical Accumulation to encode parse tree structures into self-attention at constant time complexity. | CS.iclr | 2019-12-21 |
| 616 | https://github.com/bert-nmt/bert-nmt}.“>Incorporating BERT Into Neural Machine Translation | JINHUA ZHU et. al. | We propose a new algorithm named BERT-fused NMT, in which we first use BERT to extract representations for an input sequence, and then the representations are fused with each layer of the encoder and decoder of the NMT model through attention mechanisms. | CS.iclr | 2019-12-21 |
| 617 | Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps | TRI DAO et. al. | We propose a differentiable family of kaleidoscope matrices, prove that all structured matrices can be represented in this form, and use them to replace hand-crafted linear maps in deep learning models. | CS.iclr | 2019-12-21 |
| 618 | Understanding Knowledge Distillation In Non-autoregressive Machine Translation | CHUNTING ZHOU et. al. | We systematically examine why knowledge distillation is crucial to the training of non-autoregressive translation (NAT) models, and propose methods to further improve the distilled data to best match the capacity of an NAT model. | CS.iclr | 2019-12-21 |
| 619 | Data-dependent Gaussian Prior Objective For Language Generation | ZUCHAO LI et. al. | We introduce an extra data-dependent Gaussian prior objective to augment the current MLE training, which is designed to capture the prior knowledge in the ground-truth data. | CS.iclr | 2019-12-21 |
| 620 | Residual Energy-Based Models For Text Generation | YUNTIAN DENG et. al. | We show that Energy-Based models when trained on the residual of an auto-regressive language model can be used effectively and efficiently to generate text. | CS.iclr | 2019-12-21 |
| 621 | Mirror-Generative Neural Machine Translation | ZAIXIANG ZHENG et. al. | In this paper, we propose the mirror-generative NMT (MGNMT), a single unified architecture that simultaneously integrates the source to target translation model, the target to source translation model, and two language models. | CS.iclr | 2019-12-21 |
| 622 | Neural Machine Translation With Universal Visual Representation | ZHUOSHENG ZHANG et. al. | This work proposed a universal visual representation for neural machine translation (NMT) using retrieved images with similar topics to source sentence, extending image applicability in NMT. | CS.iclr | 2019-12-21 |
| 623 | Improving Neural Language Generation With Spectrum Control | LINGXIAO WANG et. al. | In this paper, we propose a novel spectrum control approach to address this degeneration problem. | CS.iclr | 2019-12-21 |
| 624 | A Survey On Document-level Neural Machine Translation: Methods And Evaluation | SAMEEN MARUF et. al. | The aim of this survey paper is to highlight the major works that have been undertaken in the space of document-level machine translation after the neural revolution, so that researchers can recognise the current state and future directions of this field. | CS.arxiv | 2019-12-18 |
| 625 | Iterative Dual Domain Adaptation For Neural Machine Translation | JIALI ZENG et. al. | In this paper, we argue that such a strategy fails to fully extract the domain-shared translation knowledge, and repeatedly utilizing corpora of different domains can lead to better distillation of domain-shared translation knowledge. | CS.arxiv | 2019-12-16 |
| 626 | Region And Object Based Panoptic Image Synthesis Through Conditional GANs | HENG WANG et. al. | In this paper, we propose and investigate a novel task named as panoptic-level image-to-image translation and a naive baseline of solving this task. | CS.arxiv | 2019-12-14 |
| 627 | Document Sub-structure In Neural Machine Translation | RADINA DOBREVA et. al. | In this work we consider the fact that documents are rarely homogeneous blocks of text, but rather consist of parts covering different topics. We create and release the data on which we run our experiments – parallel corpora for three language pairs (Chinese-English, French-English, Bulgarian-English) from Wikipedia biographies, which we extract automatically, preserving the boundaries of sections within the articles. | CS.arxiv | 2019-12-13 |
| 628 | MetaMT,a MetaLearning Method Leveraging Multiple Domain Data For Low Resource Machine Translation | RUMENG LI et. al. | MetaMT,a MetaLearning Method Leveraging Multiple Domain Data For Low Resource Machine Translation | CS.arxiv | 2019-12-11 |
| 629 | Unsupervised Neural Dialect Translation With Commonality And Diversity Modeling | YU WAN et. al. | In this paper, we investigate how to exploit the commonality and diversity between dialects thus to build unsupervised translation models merely accessing to monolingual data. In order to examine the effectiveness of the proposed models, we collect 20 million monolingual corpus for each of Mandarin and Cantonese, which are official language and the most widely used dialect in China. | CS.arxiv | 2019-12-11 |
| 630 | Machine Translation With Cross-lingual Word Embeddings | MARCO BERLOT et. al. | Machine Translation With Cross-lingual Word Embeddings | CS.arxiv | 2019-12-10 |
| 631 | Forecasting Future Action Sequences With Attention: A New Approach To Weakly Supervised Action Forecasting | YAN BIN NG et. al. | We present a method to forecast actions for the unseen future of the video using a neural machine translation technique that uses encoder-decoder architecture. | CS.arxiv | 2019-12-10 |
| 632 | Homograph Disambiguation Through Selective Diacritic Restoration | SAWSAN ALQAHTANI et. al. | In this paper, we propose approaches for automatically marking a subset of words for diacritic restoration, which leads to selective homograph disambiguation. | CS.arxiv | 2019-12-09 |
| 633 | Cost-Sensitive Training For Autoregressive Models | IRINA SAPARINA et. al. | In this paper, we follow the learning-to-search approach (Daum\’e III et al., 2009; Leblond et al., 2018) and investigate its several components. | CS.arxiv | 2019-12-08 |
| 634 | PidginUNMT: Unsupervised Neural Machine Translation From West African Pidgin To English | KELECHI OGUEJI et. al. | In this work, we perform the first NLP work on the most popular variant of the language, providing three major contributions. | CS.arxiv | 2019-12-07 |
| 635 | Document Network Embedding: Coping For Missing Content And Missing Links | JEAN DUPUY et. al. | To tackle this issue, assuming that the topology of the network and the content of the documents correlate, we propose to estimate the missing node representations from the available content representations, and conversely. | CS.arxiv | 2019-12-06 |
| 636 | Explaining Sequence-Level Knowledge Distillation As Data-Augmentation For Neural Machine Translation | MITCHELL A. GORDON et. al. | Why does pre-processing MT data with SLKD help us train smaller models? | CS.arxiv | 2019-12-06 |
| 637 | Machine Translation Evaluation Meets Community Question Answering | FRANCISCO GUZMÁN et. al. | We explore the applicability of machine translation evaluation (MTE) methods to a very different problem: answer ranking in community Question Answering. | CS.arxiv | 2019-12-06 |
| 638 | Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation | NAVEEN ARIVAZHAGAN et. al. | We investigate the problem of simultaneous machine translation of long-form speech content. | CS.arxiv | 2019-12-06 |
| 639 | Exploration Of Neural Machine Translation In Autoformalization Of Mathematics In Mizar | QINGXIANG WANG et. al. | In this paper we share several experiments trying to automatically translate informal mathematics into formal mathematics. | CS.arxiv | 2019-12-05 |
| 640 | Neural Machine Translation: A Review And Survey | FELIX STAHLBERG | In this work we will trace back the origins of modern NMT architectures to word and sentence embeddings and earlier examples of the encoder-decoder network family. | CS.arxiv | 2019-12-04 |
| 641 | A Resource For Computational Experiments On Mapudungun | MINGJUN DUAN et. al. | We present a resource for computational experiments on Mapudungun, a polysynthetic indigenous language spoken in Chile with upwards of 200 thousand speakers. | CS.arxiv | 2019-12-03 |
| 642 | Multimodal Machine Translation Through Visuals And Speech | UMUT SULUBACAK et. al. | This survey reviews the major data resources for these tasks, the evaluation campaigns concentrated around them, the state of the art in end-to-end and pipeline approaches, and also the challenges in performance evaluation. | CS.arxiv | 2019-11-28 |
| 643 | DiscoTK: Using Discourse Structure For Machine Translation Evaluation | SHAFIQ JOTY et. al. | We present novel automatic metrics for machine translation evaluation that use discourse structure and convolution kernels to compare the discourse tree of an automatic translation with that of the human reference. | CS.arxiv | 2019-11-28 |
| 644 | Jejueo Datasets For Machine Translation And Speech Synthesis | KYUBYONG PARK et. al. | Motivated by this, we construct two new Jejueo datasets: Jejueo Interview Transcripts (JIT) and Jejueo Single Speaker Speech (JSS). | CS.arxiv | 2019-11-27 |
| 645 | Findings Of The 2016 WMT Shared Task On Cross-lingual Pronoun Prediction | LIANE GUILLOU et. al. | We describe the design, the evaluation setup, and the results of the 2016 WMT shared task on cross-lingual pronoun prediction. | CS.arxiv | 2019-11-27 |
| 646 | Generating Commit Messages From Git Diffs | S. R. P. VAN HAL et. al. | This work aims to reproduce a prominent research paper in this field, as well as attempt to improve upon their results by proposing a novel preprocessing technique. | CS.arxiv | 2019-11-26 |
| 648 | AttentionGAN: Unpaired Image-to-Image Translation Using Attention-Guided Generative Adversarial Networks | HAO TANG et. al. | In this paper, we propose a new Attention-Guided Generative Adversarial Networks (AttentionGAN) for the unpaired image-to-image translation task. | CS.arxiv | 2019-11-26 |
| 649 | Neural Machine Translation With Explicit Phrase Alignment | JIACHENG ZHANG et. al. | To alleviate these problems, we propose to introduce explicit phrase alignment into the translation process of arbitrary NMT models. | CS.arxiv | 2019-11-26 |
| 650 | Word-Class Embeddings For Multiclass Text Classification | ALEJANDRO MOREO et. al. | We propose (supervised) word-class embeddings (WCEs), and show that, when concatenated to (unsupervised) pre-trained word embeddings, they substantially facilitate the training of deep-learning models in multiclass classification by topic. | CS.arxiv | 2019-11-26 |
| 651 | Learning To Reuse Translations: Guiding Neural Machine Translation With Examples | QIAN CAO et. al. | In this paper, we study the problem of enabling neural machine translation (NMT) to reuse previous translations from similar examples in target prediction. | CS.arxiv | 2019-11-25 |
| 652 | Korean-to-Chinese Machine Translation Using Chinese Character As Pivot Clue | JEONGHYEOK PARK et. al. | Motivated by this, we propose a simple linguistically motivated solution to improve the performance of the Korean-to-Chinese neural machine translation model by using their common vocabulary. | CS.arxiv | 2019-11-25 |
| 653 | HauWE: Hausa Words Embedding For Natural Language Processing | IDRIS ABDULMUMIN et. al. | This work presents words embedding models using Word2Vec’s Continuous Bag of Words (CBoW) and Skip Gram (SG) models. | CS.arxiv | 2019-11-25 |
| 654 | Non-autoregressive Transformer By Position Learning | YU BAO et. al. | In this study, we propose PNAT, which incorporates positions as a latent variable into the text generative process. | CS.arxiv | 2019-11-24 |
| 655 | JParaCrawl: A Large Scale Web-Based English-Japanese Parallel Corpus | MAKOTO MORISHITA et. al. | We constructed a parallel corpus for English-Japanese, for which the amount of publicly available parallel corpora is still limited. We constructed the parallel corpus by broadly crawling the web and automatically aligning parallel sentences. | CS.arxiv | 2019-11-24 |
| 656 | Go From The General To The Particular: Multi-Domain Translation With Domain Transformation Networks | YONG WANG et. al. | Previous work shows that the standard neural machine translation (NMT) model, trained on mixed-domain data, generally captures the general knowledge, but misses the domain-specific knowledge. | CS.arxiv | 2019-11-22 |
| 657 | A Hybrid Morpheme-Word Representation For Machine Translation Of Morphologically Rich Languages | MINH-THANG LUONG et. al. | We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme, but word boundaries are respected at all stages of the translation process. | CS.arxiv | 2019-11-19 |
| 658 | DLBricks: Composable Benchmark Generation To Reduce Deep Learning Benchmarking Effort On CPUs (Extended) | CHENG LI et. al. | This paper proposes DLBricks, a composable benchmark generation design that reduces the effort of developing, maintaining, and running DL benchmarks on CPUs. | CS.arxiv | 2019-11-18 |
| 659 | Contribution Au Niveau De L’Approche Indirecte À Base De Transfert Dans La Traduction Automatique | SADIK BESSOU | In this thesis, we address several important issues concerning the morphological analysis of Arabic language applied to textual data and machine translation. | CS.arxiv | 2019-11-16 |
| 660 | Are Sixteen Heads Really Better Than One? | PAUL MICHEL et. al. | However we observe that, in practice, a large proportion of attention heads can be removed at test time without significantly impacting performance, and that some layers can even be reduced to a single head. | CS.nips | 2019-11-15 |
| 661 | Neural Machine Translation With Soft Prototype | YIREN WANG et. al. | In this work, we propose a new framework that introduces a soft prototype into the encoder-decoder architecture, which allows the decoder to have indirect access to both past and future information, such that each target word can be generated based on the better global understanding. | CS.nips | 2019-11-15 |
| 662 | Lookahead Optimizer: K Steps Forward, 1 Step Back | MICHAEL ZHANG et. al. | In this paper, we propose a new optimization algorithm, Lookahead, that is orthogonal to these previous approaches and iteratively updates two sets of weights. | CS.nips | 2019-11-15 |
| 663 | Fast Structured Decoding For Sequence Models | ZHIQING SUN et. al. | Specifically, we design an efficient approximation for Conditional Random Fields (CRF) for non-autoregressive sequence models, and further propose a dynamic transition technique to model positional contexts in the CRF. | CS.nips | 2019-11-15 |
| 664 | Sequence Modeling With Unconstrained Generation Order | DMITRII EMELIANENKO et. al. | In contrast, we propose a more general model that can generate the output sequence by inserting tokens in any arbitrary order. | CS.nips | 2019-11-15 |
| 665 | Cross-lingual Language Model Pretraining | ALEXIS CONNEAU et. al. | In this work, we extend this approach to multiple languages and show the effectiveness of cross-lingual pretraining. | CS.nips | 2019-11-15 |
| 666 | Levenshtein Transformer | JIATAO GU et. al. | In this work, we develop Levenshtein Transformer, a new partially autoregressive model devised for more flexible and amenable sequence generation. | CS.nips | 2019-11-15 |
| 667 | A Tensorized Transformer For Language Modeling | XINDIAN MA et. al. | In this paper, based on the ideas of tensor decomposition and parameters sharing, we propose a novel self-attention model (namely Multi-linear attention) with Block-Term Tensor Decomposition (BTD). | CS.nips | 2019-11-15 |
| 668 | Comparing Unsupervised Word Translation Methods Step By Step | MAREIKE HARTMANN et. al. | We focus on the first step and compare distribution matching techniques in the context of language pairs for which mixed training stability and evaluation scores have been reported. | CS.nips | 2019-11-15 |
| 669 | Compositional De-Attention Networks | YI TAY et. al. | This paper proposes a new quasi-attention that is compositional in nature, i.e., learning whether to \textit{add}, \textit{subtract} or \textit{nullify} a certain vector when learning representations. | CS.nips | 2019-11-15 |
| 670 | GPipe: Efficient Training Of Giant Neural Networks Using Pipeline Parallelism | YANPING HUANG et. al. | To address the need for efficient and task-independent model parallelism, we introduce TensorPipe, a pipeline parallelism library that allows scaling any network that can be expressed as a sequence of layers. | CS.nips | 2019-11-15 |
| 671 | Ouroboros: On Accelerating Training Of Transformer-Based Language Models | QIAN YANG et. al. | We propose the first model-parallel algorithm that speeds the training of Transformer-based language models. | CS.nips | 2019-11-15 |
| 672 | Non-Intrusive Load Monitoring With An Attention-based Deep Neural Network | ANTONIO M. SUDOSO et. al. | In this paper, we propose a deep neural network that combines a regression subnetwork with a classification subnetwork for solving the NILM problem. | CS.arxiv | 2019-11-15 |
| 673 | Memory Efficient Adaptive Optimization | ROHAN ANIL et. al. | We describe an effective and flexible adaptive optimization method with greatly reduced memory overhead. | CS.nips | 2019-11-15 |
| 674 | Bayesian Layers: A Module For Neural Network Uncertainty | DUSTIN TRAN et. al. | We describe Bayesian Layers, a module designed for fast experimentation with neural network uncertainty. | CS.nips | 2019-11-15 |
| 675 | Optimal Mini-Batch Size Selection For Fast Gradient Descent | MICHAEL P. PERRONE et. al. | This paper presents a methodology for selecting the mini-batch size that minimizes Stochastic Gradient Descent (SGD) learning time for single and multiple learner problems. | CS.arxiv | 2019-11-14 |
| 676 | Diversity By Phonetics And Its Application In Neural Machine Translation | ABDUL RAFAE KHAN et. al. | We introduce a powerful approach for Neural Machine Translation (NMT), whereby, during training and testing, together with the input we provide its phonetic encoding and the variants of such an encoding. | CS.arxiv | 2019-11-11 |
| 677 |