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.