A Lexicalized Reordering Model for Hierarchical Phrase-based Translation

Lexicalized reordering model plays a central role in phrase-based statistical machine translation systems. The reordering model specifies the orientation for each phrase and calculates its probability conditioned on the phrase. In this paper, we describe the necessity and the challenge of introducing such a reordering model for hierarchical phrase-based translation. To deal with the challenge, we propose a novel lexicalized reordering model which is built directly on synchronous rules. For each target phrase contained in a rule, we calculate its orientation probability conditioned on the rule. We test our model on both small and large scale data. On NIST machine translation test sets, our reordering model achieved a 0.6-1.2 BLEU point improvements for Chinese-English translation over a strong baseline hierarchical phrase-based system.