Sciweavers

ACL
2006

Left-to-Right Target Generation for Hierarchical Phrase-Based Translation

13 years 5 months ago
Left-to-Right Target Generation for Hierarchical Phrase-Based Translation
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 targetnormalized form is based on an Earlystyle top down parser on the source side. The target-normalized form coupled with our top down parser implies a left-toright 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.
Taro Watanabe, Hajime Tsukada, Hideki Isozaki
Added 30 Oct 2010
Updated 30 Oct 2010
Type Conference
Year 2006
Where ACL
Authors Taro Watanabe, Hajime Tsukada, Hideki Isozaki
Comments (0)