mlsanityData to 7 Oct 2026

Learning to Remember Translation History with a Continuous Cache

arXiv 1711.09367 ↗First posted 26 Nov 2017cs.CLcited by 39

Not on the map. Why?

Abstract (arXiv)

Existing neural machine translation (NMT) models generally translate sentences in isolation, missing the opportunity to take advantage of document-level information. In this work, we propose to augment NMT models with a very light-weight cache-like memory network, which stores recent hidden representations as translation history. The probability distribution over generated words is updated online depending on the translation history retrieved from the memory, endowing NMT models with the capability to dynamically adapt over time. Experiments on multiple domains with different topics and styles show the effectiveness of the proposed approach with negligible impact on the computational cost.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 5; 2023: 12; 2024: 5; 2025: 2.

39 papers.

Sort:

By area:

  1. 2023Document-Level Machine Translation with Large Language Modelscited by 90
  2. 2024Adapting Large Language Models for Document-Level Machine Translationcited by 59
  3. 2021Measuring and Increasing Context Usage in Context-Aware Machine Translationcited by 48
  4. 2021Fast Nearest Neighbor Machine Translationcited by 37
  5. 2021GNN-LM: Language Modeling based on Global Contexts via GNNcited by 27
  6. 2023Escaping the sentence-level paradigm in machine translationcited by 27
  7. 2021Do Context-Aware Translation Models Pay the Right Attention?cited by 21
  8. 2021Modeling Bilingual Conversational Characteristics for Neural Chat Translationcited by 18
  9. 2022Towards Robust k-Nearest-Neighbor Machine Translationcited by 15
  10. 2021Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbotscited by 14
  11. 2021Diverse Pretrained Context Encodings Improve Document Translationcited by 13
  12. 2021Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Modelscited by 12
27 more
  1. 2021Towards Making the Most of Dialogue Characteristics for Neural Chat Translationcited by 12
  2. 2021Towards User-Driven Neural Machine Translationcited by 10
  3. 2024Investigating Length Issues in Document-level Machine Translationcited by 10
  4. 2022Integrating Vectorized Lexical Constraints for Neural Machine Translationcited by 9
  5. 2023Training and Meta-Evaluating Machine Translation Evaluation Metrics at the Paragraph Levelcited by 9
  6. 2021Non-Parametric Online Learning from Human Feedback for Neural Machine Translationcited by 8
  7. 2021Faster Nearest Neighbor Machine Translationcited by 8
  8. 2023Improving Long Context Document-Level Machine Translationcited by 8
  9. 2022Scheduled Multi-task Learning for Neural Chat Translationcited by 7
  10. 2022Focused Concatenation for Context-Aware Neural Machine Translationcited by 7
  11. 2021Rethinking Nearest Neighbors for Visual Classificationcited by 6
  12. 2023Nearest Neighbors Meet Deep Neural Networks for Point Cloud Analysiscited by 5
  13. 2023Challenges in Context-Aware Neural Machine Translationcited by 5
  14. 2022Modeling Context With Linear Attention for Scalable Document-Level Translationcited by 3
  15. 2023A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translationcited by 3
  16. 2024Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approachcited by 3
  17. 2023Exploring Paracrawl for Document-level Neural Machine Translationcited by 2
  18. 2023Improving Word Sense Disambiguation in Neural Machine Translation with Salient Document Contextcited by 2
  19. 2023Cached Transformers: Improving Transformers with Differentiable Memory Cachecited by 2
  20. 2024Sequence Shortening for Context-Aware Machine Translationcited by 2
  21. 2024Context-Aware Machine Translation with Source Coreference Explanationcited by 2
  22. 2025GRAFT: A Graph-based Flow-aware Agentic Framework for Document-level Machine Translationcited by 2
  23. 2021Revisiting Context Choices for Context-aware Machine Translationcited by 1
  24. 2023Context-aware Neural Machine Translation for English-Japanese Business Scene Dialoguescited by 1
  25. 2025Discourse Graph Guided Document Translation with Large Language Modelscited by 1
  26. 2021Representation Memorization for Fast Learning New Knowledge without Forgettingcited by 0
  27. 2023On Search Strategies for Document-Level Neural Machine Translationcited by 0