A novel dependency based word-level reordering model for phrased-based translation

Phrase based statistic MT (SMT) is an important milestone in MT. However, the translation model in the phrase based SMT is structure free which limits its reordering capacity to some extent. In order to enhance the reordering capacity of phrase based SMT, in this paper we propose a head-modifier relation based reordering model, which exploits the way how to utilize the structured linguistic analysis information in source language. Within very small size of reordering model, we enhance the performance of the phrase based SMT significantly.