mlsanityData to 7 Oct 2026

Neural Machine Translation with Supervised Attention

arXiv 1609.04186 ↗First posted 14 Sep 2016cs.CLcited by 31

Not on the map. Why?

Abstract (arXiv)

The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse than conventional alignment models in aligment accuracy. In this paper, we analyze and explain this issue from the point view of re- ordering, and propose a supervised attention which is learned with guidance from conventional alignment models. Experiments on two Chinese-to-English translation tasks show that the super- vised attention mechanism yields better alignments leading to substantial gains over the standard attention based NMT.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 11; 2023: 1; 2024: 3; 2025: 1; 2026: 1.

31 papers.

Sort:

By area:

  1. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  2. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
  3. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  4. 2022A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generationcited by 25
  5. 2021Do Context-Aware Translation Models Pay the Right Attention?cited by 21
  6. 2021Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMTcited by 21
  7. 2022Modeling Dual Read/Write Paths for Simultaneous Machine Translationcited by 21
  8. 2021Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Modelcited by 18
  9. 2021TranSmart: A Practical Interactive Machine Translation Systemcited by 17
  10. 2022Gaussian Multi-head Attention for Simultaneous Machine Translationcited by 17
  11. 2022Inducing and Using Alignments for Transition-based AMR Parsingcited by 11
  12. 2024DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignmentcited by 9
19 more
  1. 2021Discrete-continuous Action Space Policy Gradient-based Attention for Image-Text Matchingcited by 8
  2. 2021Few-Shot Semantic Parsing for New Predicatescited by 7
  3. 2022Guiding Visual Question Answering with Attention Priorscited by 7
  4. 2022Hierarchical Phrase-based Sequence-to-Sequence Learningcited by 7
  5. 2021Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learningcited by 5
  6. 2021Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attentioncited by 5
  7. 2021Attention Forcing for Machine Translationcited by 3
  8. 2022Supervised Attention in Sequence-to-Sequence Models for Speech Recognitioncited by 3
  9. 2022Word Alignment in the Era of Deep Learning: A Tutorialcited by 3
  10. 2025SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modelingcited by 3
  11. 2022Supervised Visual Attention for Simultaneous Multimodal Machine Translationcited by 2
  12. 2022Unifying the Convergences in Multilingual Neural Machine Translationcited by 2
  13. 2021Metric-Type Identification for Multi-Level Header Numerical Tables in Scientific Paperscited by 0
  14. 2021An empirical analysis of phrase-based and neural machine translationcited by 0
  15. 2022Third-Party Aligner for Neural Word Alignmentscited by 0
  16. 2023RCMHA: Relative Convolutional Multi-Head Attention for Natural Language Modellingcited by 0
  17. 2024Depth-induced Saliency Comparison Network for Diagnosis of Alzheimer's Disease via Jointly Analysis of Visual Stimuli and Eye Movementscited by 0
  18. 2024An Energy-based Model for Word-level AutoCompletion in Computer-aided Translationcited by 0
  19. 2026Pretrained Multilingual Transformers Reveal Quantitative Distance Between Human Languagescited by 0