Paper: Head-modifier Relation based Non-lexical Reordering Model for Phrase-Based Translation

ACL ID C10-2086
Title Head-modifier Relation based Non-lexical Reordering Model for Phrase-Based Translation
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

Phrase-based statistical MT (SMT) is a milestone in MT. However, the transla- tion model in the phrase based SMT is structure free which greatly limits its reordering capacity. To address this is- sue, we propose a non-lexical head- modifier based reordering model on word level by utilizing constituent based parse tree in source side. Our experi- mental results on the NIST Chinese- English benchmarking data show that, with a very small size model, our me- thod significantly outperforms the base- line by 1.48% bleu score.