Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder
Computation and Language
2017-07-19 v1
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.
Cite
@article{arxiv.1707.05436,
title = {Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder},
author = {Huadong Chen and Shujian Huang and David Chiang and Jiajun Chen},
journal= {arXiv preprint arXiv:1707.05436},
year = {2017}
}
Comments
Accepted as a long paper by ACL 2017