mlsanityData to 14 Oct 2026

Revisiting Context Choices for Context-aware Machine Translation

arXiv 2109.02995 ↗First posted 7 Sep 2021cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

One of the most popular methods for context-aware machine translation (MT) is to use separate encoders for the source sentence and context as multiple sources for one target sentence. Recent work has cast doubt on whether these models actually learn useful signals from the context or are improvements in automatic evaluation metrics just a side-effect. We show that multi-source transformer models improve MT over standard transformer-base models even with empty lines provided as context, but the translation quality improves significantly (1.51 - 2.65 BLEU) when a sufficient amount of correct context is provided. We also show that even though randomly shuffling in-domain context can also improve over baselines, the correct context further improves translation quality and random out-of-domain context further degrades it.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 7 Sep 2021.

Builds on

22 of 37 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  3. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  4. 2018Marian: Fast Neural Machine Translation in C++cited by 203
  5. 2018Context-Aware Neural Machine Translation Learns Anaphora Resolutioncited by 97
  6. 2017Neural Machine Translation with Extended Contextcited by 95
  7. 2018Document-Level Neural Machine Translation with Hierarchical Attention Networkscited by 85
  8. 2018Improving the Transformer Translation Model with Document-Level Contextcited by 74
  9. 2019Selective Attention for Context-aware Neural Machine Translationcited by 60
  10. 2019Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translationcited by 56
  11. 2019When and Why is Document-level Context Useful in Neural Machine Translation?cited by 45
  12. 2017Learning to Remember Translation History with a Continuous Cachecited by 39
10 more
  1. 2017Does Neural Machine Translation Benefit from Larger Context?cited by 38
  2. 2016Multi-Source Neural Translationcited by 37
  3. 2020Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translationcited by 34
  4. 2020Multi-Encoder-Decoder Transformer for Code-Switching Speech Recognitioncited by 28
  5. 2019JParaCrawl: A Large Scale Web-Based English-Japanese Parallel Corpuscited by 21
  6. 2018MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editingcited by 13
  7. 2019Using Whole Document Context in Neural Machine Translationcited by 9
  8. 2020Document-aligned Japanese-English Conversation Parallel Corpuscited by 7
  9. 2020Can Your Context-Aware MT System Pass the DiP Benchmark Tests? : Evaluation Benchmarks for Discourse Phenomena in Machine Translationcited by 6
  10. 2020Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translationcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024On Measuring Context Utilization in Document-Level MT Systemscited by 9