Reordering Model Using Syntactic Information of a Source Tree for Statistical Machine Translation

This paper presents a reordering model using syntactic information of a source tree for phrase-based statistical machine translation. The proposed model is an extension of ISTITG (imposing source tree on inversion transduction grammar) constraints. In the proposed method, the target-side word order is obtained by rotating nodes of the source-side parse-tree. We modeled the node rotation, monotone or swap, using word alignments based on a training parallel corpus and sourceside parse-trees. The model efficiently suppresses erroneous target word orderings, especially global orderings. Furthermore, the proposed method conducts a probabilistic evaluation of target word reorderings. In Englishto-Japanese and English-to-Chinese translation experiments, the proposed method resulted in a 0.49-point improvement (29.31 to 29.80) and a 0.33-point improvement (18.60 to 18.93) in word BLEU-4 compared with IST-ITG constraints, respectively. This indicates the validity of the proposed reordering model.