mlsanityData to 14 Oct 2026

Context-Aware Neural Machine Translation Learns Anaphora Resolution

arXiv 1805.10163 ↗First posted 25 May 2018cs.CLcited by 97

Not on the map. Why?

Abstract (arXiv)

Standard machine translation systems process sentences in isolation and hence ignore extra-sentential information, even though extended context can both prevent mistakes in ambiguous cases and improve translation coherence. We introduce a context-aware neural machine translation model designed in such way that the flow of information from the extended context to the translation model can be controlled and analyzed. We experiment with an English-Russian subtitles dataset, and observe that much of what is captured by our model deals with improving pronoun translation. We measure correspondences between induced attention distributions and coreference relations and observe that the model implicitly captures anaphora. It is consistent with gains for sentences where pronouns need to be gendered in translation. Beside improvements in anaphoric cases, the model also improves in overall BLEU, both over its context-agnostic version (+0.7) and over simple concatenation of the context and source sentences (+0.6).

Key facts. Cited by 97 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 24; 2022: 12; 2023: 29; 2024: 12; 2025: 15; 2026: 5.

97 papers.

Sort:

By area:

  1. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 429
  2. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  3. 2023Document-Level Machine Translation with Large Language Modelscited by 90
  4. 2023Neurons in Large Language Models: Dead, N-gram, Positionalcited by 88
  5. 2023Inseq: An Interpretability Toolkit for Sequence Generation Modelscited by 78
  6. 2022Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translationcited by 61
  7. 2023Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOMcited by 59
  8. 2024Adapting Large Language Models for Document-Level Machine Translationcited by 59
  9. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  10. 2022Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformercited by 45
  11. 2023Quantifying Context Mixing in Transformerscited by 43
  12. 2021Generate, Annotate, and Learn: NLP with Synthetic Textcited by 42
38 more
  1. 2021Sparse Attention with Linear Unitscited by 41
  2. 2021When Does Translation Require Context? A Data-driven, Multilingual Explorationcited by 36
  3. 2022DiscoScore: Evaluating Text Generation with BERT and Discourse Coherencecited by 36
  4. 2021DAGN: Discourse-Aware Graph Network for Logical Reasoningcited by 28
  5. 2023Escaping the sentence-level paradigm in machine translationcited by 27
  6. 2022F-coref: Fast, Accurate and Easy to Use Coreference Resolutioncited by 24
  7. 2021On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classificationcited by 21
  8. 2021Do Context-Aware Translation Models Pay the Right Attention?cited by 21
  9. 2023Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editingcited by 21
  10. 2023A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translationcited by 19
  11. 2024Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trendscited by 19
  12. 2021Modeling Bilingual Conversational Characteristics for Neural Chat Translationcited by 18
  13. 2021Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matricescited by 17
  14. 2024Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?cited by 17
  15. 2021The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architecturescited by 16
  16. 2021On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformerscited by 14
  17. 2021Diverse Pretrained Context Encodings Improve Document Translationcited by 13
  18. 2024Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructionscited by 13
  19. 2021Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Modelscited by 12
  20. 2021Towards Making the Most of Dialogue Characteristics for Neural Chat Translationcited by 12
  21. 2023Document-Level Language Models for Machine Translationcited by 12
  22. 2025AFRIDOC-MT: Document-level MT Corpus for African Languagescited by 11
  23. 2025Learning Task Representations from In-Context Learningcited by 11
  24. 2025Multilingual Contextualization of Large Language Models for Document-Level Machine Translationcited by 11
  25. 2023SketchXAI: A First Look at Explainability for Human Sketchescited by 10
  26. 2023Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modellingcited by 10
  27. 2024Investigating Length Issues in Document-level Machine Translationcited by 10
  28. 2021What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysiscited by 9
  29. 2021Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Informationcited by 9
  30. 2023Contextual Label Projection for Cross-Lingual Structured Predictioncited by 9
  31. 2022Benchmarking Language Models for Code Syntax Understandingcited by 8
  32. 2023Improving Long Context Document-Level Machine Translationcited by 8
  33. 2021A Comparison of Approaches to Document-level Machine Translationcited by 7
  34. 2021YANMTT: Yet Another Neural Machine Translation Toolkitcited by 7
  35. 2022Scheduled Multi-task Learning for Neural Chat Translationcited by 7
  36. 2022Focused Concatenation for Context-Aware Neural Machine Translationcited by 7
  37. 2023Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpuscited by 7
  38. 2023Quantifying the Plausibility of Context Reliance in Neural Machine Translationcited by 7

50 most cited of 97 All 97 (JSON)