Abstract
In statistical machine translation (SMT), syntax-based pre-ordering of the source language is an effective method for dealing with language pairs where there are great differences in their respective word orders. This paper introduces a novel pre-ordering approach based on dependency parsing for Chinese-English SMT. We present a set of dependency-based preordering rules which improved the BLEU score by 1.61 on the NIST 2006 evaluation data. We also investigate the accuracy of the rule set by conducting human evaluations. © 2014 Association for Computational Linguistics.
Cite
CITATION STYLE
Cai, J., Utiyama, M., Sumita, E., & Zhang, Y. (2014). Dependency-based pre-ordering for Chinese-English machine translation. In 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference (Vol. 2, pp. 155–160). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/p14-2026
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
