Abstract
This paper introduces a novel word re-ordering model for statistical machine translation that employs a shift-reduce parser for inversion transduction grammars. The proposed model also solves article generation problems simultaneously with word re-ordering. We applied it to the post-ordering of phrase-based machine translation (PBMT) for Japanese-to-English patent translation tasks. Our experimental results suggest that our method achieves a significant improvement of +3.15 BLEU scores against 29.99 BLEU scores of the baseline PBMT system.
