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.(1) |
Year | DOI | Venue |
---|---|---|
2017 | 10.18653/v1/P17-1177 | PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1 |
DocType | Volume | Citations |
Conference | abs/1707.05436 | 25 |
PageRank | References | Authors |
0.73 | 9 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huadong Chen | 1 | 32 | 2.82 |
Shujian Huang | 2 | 158 | 28.78 |
David Chiang | 3 | 2843 | 144.76 |
Jiajun Chen | 4 | 244 | 45.03 |