Research map / Architectures and efficiency / Attention and transformers
Syntax-Directed Attention for Neural Machine Translation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace linear-distance attention with syntax-distance-constrained attention | GlobalAtt NMT · ZH-EN | BLEU: 1.32 BLEU points | Helped |
| Replace linear-distance attention with syntax-distance-constrained attention | GlobalAtt NMT · EN-DE | BLEU | Helped |
| Add a syntax-directed context alongside global context | GlobalAtt NMT · ZH-EN | BLEU: 2.37 BLEU points | Helped |
| Add a syntax-directed context alongside global context | GlobalAtt NMT · EN-DE | BLEU | Helped |
| Use syntax-distance constraint instead of linear-distance constraint | LocalAtt NMT · ZH-EN | BLEU: 0.97 BLEU points | Helped |
| Use syntax-distance constraint instead of linear-distance constraint | LocalAtt NMT · EN-DE | BLEU | Helped |
| Use syntax-distance constraint instead of Chen et al.'s dependency representation | GlobalAtt NMT · ZH-EN | BLEU: 0.47 BLEU points | Helped |
| Use syntax-directed attention instead of Chen et al.'s dependency representation | GlobalAtt NMT · EN-DE | BLEU | Helped |
| Add syntax-directed context rather than Chen et al.'s dependency-based model | GlobalAtt NMT · ZH-EN | BLEU: 0.79 BLEU points | Helped |
| Add syntax-directed context rather than Chen et al.'s dependency-based model | GlobalAtt NMT · EN-DE | BLEU | Helped |
Closest papers by meaning
- Neural Machine Translation with Joint Representation (AAAI 2020 · similarity 0.89)
- Asynchronous Bidirectional Decoding for Neural Machine Translation (AAAI 2018 · similarity 0.88)
- Alignment-Enhanced Transformer for Constraining NMT with Pre-Specified Translations (AAAI 2020 · similarity 0.88)
- Attention-via-Attention Neural Machine Translation (AAAI 2018 · similarity 0.88)
- Attention is All you Need (NeurIPS 2017 · similarity 0.88)
- Exploring the Translation Mechanism of Large Language Models (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.