Paper: Dependency-based Pre-ordering for Chinese-English Machine Translation

ACL ID P14-2026
Title Dependency-based Pre-ordering for Chinese-English Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

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.