Dependency-based Pre-ordering for Chinese-English Machine Translation
Jingsheng Cai, Masao Utiyama, Eiichiro Sumita, Yujie Zhang · 2014
In statistical machine translation (SMT), syntax-based pre-ordering of the source language is an effective method for deal-ing with language pairs where there are great differences in their respective word orders. This paper introduces a novel pre-ordering approach based on depen-dency parsing for Chinese-English SMT. We present a set of dependency-based pre-ordering rules which improved the BLEU score by 1.61 on the NIST 2006 evalua-tion data. We also investigate the accuracy of the rule set by conducting human eval-uations. 1