Abstract | ||
---|---|---|
We present a hierarchical phrase-based statistical machine translation in which a target sentence is efficiently generated in left-to-right order. The model is a class of synchronous-CFG with a Greibach Normal Form-like structure for the projected production rule: The paired target-side of a production rule takes a phrase prefixed form. The decoder for the target-normalized form is based on an Early-style top down parser on the source side. The target-normalized form coupled with our top down parser implies a left-to-right generation of translations which enables us a straightforward integration with ngram language models. Our model was experimented on a Japanese-to-English newswire translation task, and showed statistically significant performance improvements against a phrase-based translation system. |
Year | DOI | Venue |
---|---|---|
2006 | 10.3115/1220175.1220273 | ACL |
Keywords | Field | DocType |
left-to-right generation,production rule,ngram language model,phrase prefixed form,hierarchical phrase-based translation,left-to-right target generation,phrase-based translation system,left-to-right order,hierarchical phrase-based statistical machine,japanese-to-english newswire translation task,target-normalized form,early-style top,language model,top down,normal form | Rule-based machine translation,Top-down parsing,Example-based machine translation,Computer science,Machine translation,Phrase,Speech recognition,Transfer-based machine translation,Artificial intelligence,Natural language processing,Sentence,Language model | Conference |
Volume | Citations | PageRank |
P06-1 | 35 | 1.46 |
References | Authors | |
15 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taro Watanabe | 1 | 572 | 36.86 |
Hajime Tsukada | 2 | 449 | 29.46 |
Hideki Isozaki | 3 | 934 | 64.50 |