Rule-based Syntactic Preprocessing for Syntax-based Machine Translation
Yuto Hatakoshi, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura · 2014
Several preprocessing techniques using syntactic information and linguistically motivated rules have been proposed to im-prove the quality of phrase-based machine translation (PBMT) output. On the other hand, there has been little work on similar techniques in the context of other trans-lation formalisms such as syntax-based SMT. In this paper, we examine whether the sort of rule-based syntactic preprocess-ing approaches that have proved beneficial for PBMT can contribute to syntax-based SMT. Specifically, we tailor a highly suc-cessful preprocessing method for English-Japanese PBMT to syntax-based SMT, and find that while the gains achievable are smaller than those for PBMT, significant improvements in accuracy can be realized. 1