mlsanityData to 7 Oct 2026

Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder

arXiv 1707.05436 ↗First posted 18 Jul 2017cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

Most neural machine translation (NMT) models are based on the sequential encoder-decoder framework, which makes no use of syntactic information. In this paper, we improve this model by explicitly incorporating source-side syntactic trees. More specifically, we propose (1) a bidirectional tree encoder which learns both sequential and tree structured representations; (2) a tree-coverage model that lets the attention depend on the source-side syntax. Experiments on Chinese-English translation demonstrate that our proposed models outperform the sequential attentional model as well as a stronger baseline with a bottom-up tree encoder and word coverage.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 1; 2023: 6; 2024: 4; 2025: 0; 2026: 1.

16 papers.

Sort:

  1. 2024Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformerscited by 24
  2. 2021Syntax-augmented Multilingual BERT for Cross-lingual Transfercited by 11
  3. 2024RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarizationcited by 10
  4. 2023Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoderscited by 6
  5. 2023Transformers as Graph-to-Graph Modelscited by 5
  6. 2021On the Relation between Syntactic Divergence and Zero-Shot Performancecited by 4
  7. 2023Structured Dialogue Discourse Parsingcited by 4
  8. 2022Syntax-guided Localized Self-attention by Constituency Syntactic Distancecited by 3
  9. 2024Tree Transformers are an Ineffective Model of Syntactic Constituencycited by 3
  10. 2023xASTNN: Improved Code Representations for Industrial Practicecited by 2
  11. 2023Neural Machine Translation with Dynamic Graph Convolutional Decodercited by 2
  12. 2021Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Networkcited by 1
4 more
  1. 2021Exploiting Rich Syntax for Better Knowledge Base Question Answeringcited by 0
  2. 2023Syntax-Aware Complex-Valued Neural Machine Translationcited by 0
  3. 2024Prediction of Translation Techniques for the Translation Processcited by 0
  4. 2026Top-down string-to-dependency Neural Machine Translationcited by 0