mlsanityData to 7 Oct 2026

Modeling Coverage for Neural Machine Translation

arXiv 1601.04811 ↗First posted 19 Jan 2016cs.CLcited by 110

Not on the map. Why?

Abstract (arXiv)

Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by jointly learning to align and translate. It tends to ignore past alignment information, however, which often leads to over-translation and under-translation. To address this problem, we propose coverage-based NMT in this paper. We maintain a coverage vector to keep track of the attention history. The coverage vector is fed to the attention model to help adjust future attention, which lets NMT system to consider more about untranslated source words. Experiments show that the proposed approach significantly improves both translation quality and alignment quality over standard attention-based NMT.

Key facts. Cited by 110 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jan 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 41; 2022: 33; 2023: 15; 2024: 9; 2025: 4; 2026: 7.

110 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMscited by 162
  3. 2021The Curious Case of Hallucinations in Neural Machine Translationcited by 161
  4. 2023End-to-End Speech Recognition: A Surveycited by 127
  5. 2018Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Interventioncited by 77
  6. 2024LLMs Will Always Hallucinate, and We Need to Live With Thiscited by 77
  7. 2021AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarizationcited by 51
  8. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  9. 2022When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognitioncited by 35
  10. 2021Prevent the Language Model from being Overconfident in Neural Machine Translationcited by 34
  11. 2021Is Sparse Attention more Interpretable?cited by 31
  12. 2021On the limit of English conversational speech recognitioncited by 30
38 more
  1. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  2. 2022A Survey on Neural Open Information Extraction: Current Status and Future Directionscited by 27
  3. 2021Progressive Multi-Granularity Training for Non-Autoregressive Translationcited by 25
  4. 2022CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognitioncited by 24
  5. 2021Keyphrase Generation for Scientific Document Retrievalcited by 23
  6. 2021Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMTcited by 21
  7. 2021Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generationcited by 19
  8. 2021Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Modelcited by 18
  9. 2021Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translationcited by 17
  10. 2022Assemble Foundation Models for Automatic Code Summarizationcited by 17
  11. 2021Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learningcited by 16
  12. 2023NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklistcited by 16
  13. 2021On the Limits of Minimal Pairs in Contrastive Evaluationcited by 15
  14. 2022Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generationcited by 15
  15. 2023From Statistical Methods to Deep Learning, Automatic Keyphrase Prediction: A Surveycited by 14
  16. 2024Word Alignment as Preference for Machine Translationcited by 14
  17. 2021Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learningcited by 13
  18. 2021Lexically Aware Semi-Supervised Learning for OCR Post-Correctioncited by 12
  19. 2023Generation of Highlights from Research Papers Using Pointer-Generator Networks and SciBERT Embeddingscited by 12
  20. 2021Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLGcited by 11
  21. 2022As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioningcited by 11
  22. 2022Multi-Document Scientific Summarization from a Knowledge Graph-Centric Viewcited by 11
  23. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  24. 2023Named Entity Recognition Based Automatic Generation of Research Highlightscited by 10
  25. 2023WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Predictioncited by 10
  26. 2023Instruction Position Matters in Sequence Generation with Large Language Modelscited by 10
  27. 2021Multi-Modal Image Captioning for the Visually Impairedcited by 8
  28. 2022R2D2: Robust Data-to-Text with Replacement Detectioncited by 8
  29. 2021Active2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translationcited by 6
  30. 2021Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?cited by 6
  31. 2021Revisiting Negation in Neural Machine Translationcited by 6
  32. 2022Compositional Generalisation with Structured Reordering and Fertility Layerscited by 6
  33. 2021A study of latent monotonic attention variantscited by 5
  34. 2021Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal informationcited by 5
  35. 2021Taming Repetition in Dialogue Generationcited by 5
  36. 2022Reducing Hallucinations in Neural Machine Translation with Feature Attributioncited by 5
  37. 2021Modeling Coverage for Non-Autoregressive Neural Machine Translationcited by 4
  38. 2021SGG: Learning to Select, Guide, and Generate for Keyphrase Generationcited by 4

50 most cited of 110 All 110 (JSON)