mlsanityData to 7 Oct 2026

Enhancing Machine Translation with Dependency-Aware Self-Attention

arXiv 1909.03149 ↗First posted 6 Sep 2019cs.CLcited by 24

Not on the map. Why?

Abstract (arXiv)

Most neural machine translation models only rely on pairs of parallel sentences, assuming syntactic information is automatically learned by an attention mechanism. In this work, we investigate different approaches to incorporate syntactic knowledge in the Transformer model and also propose a novel, parameter-free, dependency-aware self-attention mechanism that improves its translation quality, especially for long sentences and in low-resource scenarios. We show the efficacy of each approach on WMT English-German and English-Turkish, and WAT English-Japanese translation tasks.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 5; 2023: 4; 2024: 4; 2025: 1; 2026: 2.

24 papers.

Sort:

By area:

  1. 2022CTC Alignments Improve Autoregressive Translationcited by 25
  2. 2023CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Taskscited by 18
  3. 2021Does injecting linguistic structure into language models lead to better alignment with brain recordings?cited by 11
  4. 2021Syntax-augmented Multilingual BERT for Cross-lingual Transfercited by 11
  5. 2021Headed-Span-Based Projective Dependency Parsingcited by 11
  6. 2022Controlled Text Reductioncited by 10
  7. 2024RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarizationcited by 10
  8. 2021Semantics-aware Attention Improves Neural Machine Translationcited by 5
  9. 2022Structural Biases for Improving Transformers on Translation into Morphologically Rich Languagescited by 5
  10. 2023ChatGPT is a Potential Zero-Shot Dependency Parsercited by 5
  11. 2021On the Relation between Syntactic Divergence and Zero-Shot Performancecited by 4
  12. 2024Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervisioncited by 4
12 more
  1. 2022Syntax-guided Localized Self-attention by Constituency Syntactic Distancecited by 3
  2. 2024Context-Aware Machine Translation with Source Coreference Explanationcited by 2
  3. 2021Enhancing the Transformer Decoder with Transition-based Syntaxcited by 1
  4. 2021Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Networkcited by 1
  5. 2023An Effective Method using Phrase Mechanism in Neural Machine Translationcited by 1
  6. 2021Combining Improvements for Exploiting Dependency Trees in Neural Semantic Parsingcited by 0
  7. 2022Schema-Free Dependency Parsing via Sequence Generationcited by 0
  8. 2023Rethinking Relation Classification with Graph Meaning Representationscited by 0
  9. 2024Leveraging Grammar Induction for Language Understanding and Generationcited by 0
  10. 2025Advancing Bangla Machine Translation Through Informal Datasetscited by 0
  11. 2026Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMscited by 0
  12. 2026Evaluating Explainable AI Attribution Methods in Neural Machine Translation via Attention-Guided Knowledge Distillationcited by 0