Name
Abstract | ||
|---|---|---|
One major drawback of phrase-based translation is that it segments an input sentence into continuous phrases. To support linguistically informed source discontinuity, in this paper we construct graphs which combine bigram and dependency relations and propose a graph-based translation model. The model segments an input graph into connected subgraphs, each of which may cover a discontinuous phrase. We use beam search to combine translations of each subgraph left-to-right to produce a complete translation. Experiments on Chinese-English and German-English tasks show that our system is significantly better than the phrase-based model by up to +1.5/+0.5 BLEU scores. By explicitly modeling the graph segmentation, our system obtains further improvement, especially on German-English. |
Year | Venue | DocType |
|---|---|---|
2016 | PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1 | Conference |
Volume | Citations | PageRank |
P16-1 | 0 | 0.34 |
References | Authors | |
21 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Liangyou Li | 1 | 2 | 2.72 |
| Andy Way | 2 | 881 | 126.78 |
| Qun Liu | 3 | 2149 | 203.11 |