mlsanityData to 14 Oct 2026

Saliency-driven Word Alignment Interpretation for Neural Machine Translation

arXiv 1906.10282 ↗First posted 25 Jun 2019cs.CLcited by 27

Not on the map. Why?

Abstract (arXiv)

Despite their original goal to jointly learn to align and translate, Neural Machine Translation (NMT) models, especially Transformer, are often perceived as not learning interpretable word alignments. In this paper, we show that NMT models do learn interpretable word alignments, which could only be revealed with proper interpretation methods. We propose a series of such methods that are model-agnostic, are able to be applied either offline or online, and do not require parameter update or architectural change. We show that under the force decoding setup, the alignments induced by our interpretation method are of better quality than fast-align for some systems, and when performing free decoding, they agree well with the alignments induced by automatic alignment tools.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 8; 2023: 8; 2024: 0; 2025: 0; 2026: 2.

27 papers.

Sort:

By area:

  1. 2023Inseq: An Interpretability Toolkit for Sequence Generation Modelscited by 78
  2. 2022Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformercited by 45
  3. 2023Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspectioncited by 44
  4. 2023Explaining How Transformers Use Context to Build Predictionscited by 43
  5. 2021Sparse Attention with Linear Unitscited by 41
  6. 2021Evaluating Saliency Methods for Neural Language Modelscited by 37
  7. 2023Using Sequences of Life-events to Predict Human Livescited by 27
  8. 2022Toxicity in Multilingual Machine Translation at Scalecited by 26
  9. 2023AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compressioncited by 26
  10. 2021Relative Importance in Sentence Processingcited by 22
  11. 2023End-to-End Simultaneous Speech Translation with Differentiable Segmentationcited by 22
  12. 2022Learning to Scaffold: Optimizing Model Explanations for Teachingcited by 20
15 more
  1. 2021TranSmart: A Practical Interactive Machine Translation Systemcited by 17
  2. 2021On the Lack of Robust Interpretability of Neural Text Classifierscited by 17
  3. 2023Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translationcited by 15
  4. 2021Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictionscited by 11
  5. 2022Robust Natural Language Processing: Recent Advances, Challenges, and Future Directionscited by 11
  6. 2021Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learningcited by 5
  7. 2022Gradient Knowledge Distillation for Pre-trained Language Modelscited by 5
  8. 2023Neural Text Sanitization with Privacy Risk Indicators: An Empirical Analysiscited by 5
  9. 2021MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learningcited by 4
  10. 2022Word Alignment in the Era of Deep Learning: A Tutorialcited by 3
  11. 2021Understanding How Encoder-Decoder Architectures Attendcited by 2
  12. 2026Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMscited by 1
  13. 2022Lost in Context? On the Sense-wise Variance of Contextualized Word Embeddingscited by 0
  14. 2022Third-Party Aligner for Neural Word Alignmentscited by 0
  15. 2026Evaluating Explainable AI Attribution Methods in Neural Machine Translation via Attention-Guided Knowledge Distillationcited by 0