mlsanityData to 7 Oct 2026

Document-Level Neural Machine Translation with Hierarchical Attention Networks

arXiv 1809.01576 ↗First posted 5 Sep 2018cs.CLcited by 85

Not on the map. Why?

Abstract (arXiv)

Neural Machine Translation (NMT) can be improved by including document-level contextual information. For this purpose, we propose a hierarchical attention model to capture the context in a structured and dynamic manner. The model is integrated in the original NMT architecture as another level of abstraction, conditioning on the NMT model's own previous hidden states. Experiments show that hierarchical attention significantly improves the BLEU score over a strong NMT baseline with the state-of-the-art in context-aware methods, and that both the encoder and decoder benefit from context in complementary ways.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 14; 2023: 23; 2024: 10; 2025: 8; 2026: 3.

85 papers.

Sort:

By area:

  1. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 401
  2. 2021A Survey of Transformerscited by 399
  3. 2021Random Feature Attentioncited by 350
  4. 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
  5. 2023Large language models effectively leverage document-level context for literary translation, but critical errors persistcited by 80
  6. 2023Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Surveycited by 71
  7. 2021Poolingformer: Long Document Modeling with Pooling Attentioncited by 60
  8. 2024Adapting Large Language Models for Document-Level Machine Translationcited by 59
  9. 2021Measuring and Increasing Context Usage in Context-Aware Machine Translationcited by 48
  10. 2021H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequencescited by 47
  11. 2021G-Transformer for Document-level Machine Translationcited by 46
  12. 2022Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literaturecited by 45
38 more
  1. 2021Generate, Annotate, and Learn: NLP with Synthetic Textcited by 42
  2. 2021When Does Translation Require Context? A Data-driven, Multilingual Explorationcited by 36
  3. 2021ABC: Attention with Bounded-memory Controlcited by 36
  4. 2022DiscoScore: Evaluating Text Generation with BERT and Discourse Coherencecited by 35
  5. 2021Hierarchical Learning for Generation with Long Source Sequencescited by 32
  6. 2023Escaping the sentence-level paradigm in machine translationcited by 27
  7. 2024DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memorycited by 27
  8. 2021Do Context-Aware Translation Models Pay the Right Attention?cited by 21
  9. 2021Investigating Failures of Automatic Translation in the Case of Unambiguous Gendercited by 20
  10. 2021BERTTune: Fine-Tuning Neural Machine Translation with BERTScorecited by 18
  11. 2021Modeling Bilingual Conversational Characteristics for Neural Chat Translationcited by 18
  12. 2022Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translationcited by 16
  13. 2023Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translationcited by 15
  14. 2023Identifying Context-Dependent Translations for Evaluation Set Productioncited by 14
  15. 2021Diverse Pretrained Context Encodings Improve Document Translationcited by 13
  16. 2021Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Modelscited by 12
  17. 2021Towards Making the Most of Dialogue Characteristics for Neural Chat Translationcited by 12
  18. 2023Document-Level Language Models for Machine Translationcited by 12
  19. 2024Learning to Plan for Language Modeling from Unlabeled Datacited by 12
  20. 2022A baseline revisited: Pushing the limits of multi-segment models for context-aware translationcited by 11
  21. 2025AFRIDOC-MT: Document-level MT Corpus for African Languagescited by 11
  22. 2025Multilingual Contextualization of Large Language Models for Document-Level Machine Translationcited by 11
  23. 2022A Call for Clarity in Beam Search: How It Works and When It Stopscited by 10
  24. 2024Investigating Length Issues in Document-level Machine Translationcited by 10
  25. 2021Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Informationcited by 9
  26. 2023A Survey on Zero Pronoun Translationcited by 9
  27. 2023Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Levelcited by 9
  28. 2021DOCmT5: Document-Level Pretraining of Multilingual Language Modelscited by 8
  29. 2023Improving Long Context Document-Level Machine Translationcited by 8
  30. 2021A Comparison of Approaches to Document-level Machine Translationcited by 7
  31. 2021Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documentscited by 7
  32. 2022Scheduled Multi-task Learning for Neural Chat Translationcited by 7
  33. 2022Focused Concatenation for Context-Aware Neural Machine Translationcited by 7
  34. 2022Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Frameworkcited by 6
  35. 2024DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translatorscited by 6
  36. 2024Recovering document annotations for sentence-level bitextcited by 6
  37. 2025Extending Automatic Machine Translation Evaluation to Book-Length Documentscited by 6
  38. 2022P-Transformer: Towards Better Document-to-Document Neural Machine Translationcited by 5

50 most cited of 85 All 85 (JSON)