Abstract | ||
---|---|---|
In this paper, we propose forest-to-string rules to enhance the expressive power of tree-to-string translation models. A forest- to-string rule is capable of capturing non- syntactic phrase pairs by describing the cor- respondence between multiple parse trees and one string. To integrate these rules into tree-to-string translation models, auxil- iary rules are introduced to provide a gen- eralization level. Experimental results show that, on the NIST 2005 Chinese-English test set, the tree-to-string model augmented with forest-to-string rules achieves a relative im- provement of 4.3% in terms of BLEU score over the original model which allows tree- to-string rules only. |
Year | Venue | Keywords |
---|---|---|
2007 | ACL | expressive power |
Field | DocType | Volume |
BLEU,Computer science,Phrase,Speech recognition,NIST,Artificial intelligence,Natural language processing,Parsing,Expressive power,Test set | Conference | P07-1 |
Citations | PageRank | References |
35 | 1.03 | 16 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yang Liu | 1 | 1568 | 126.97 |
Yun Huang | 2 | 49 | 5.83 |
Qun Liu | 3 | 2149 | 203.11 |
Shouxun Lin | 4 | 963 | 56.20 |