Abstract
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.- Anthology ID:
- P17-1177
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Regina Barzilay, Min-Yen Kan
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1936–1945
- Language:
- URL:
- https://aclanthology.org/P17-1177
- DOI:
- 10.18653/v1/P17-1177
- Cite (ACL):
- Huadong Chen, Shujian Huang, David Chiang, and Jiajun Chen. 2017. Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1936–1945, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder (Chen et al., ACL 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/P17-1177.pdf
- Code
- howardchenhd/Syntax-awared-NMT