文章基本信息

标题：Otedama: Fast Rule-Based Pre-Ordering for Machine Translation
本地全文：下载
作者：Julian Hitschler ; Laura Jehl ; Sariya Karimova 等
期刊名称：The Prague Bulletin of Mathematical Linguistics
印刷版ISSN：0032-6585
电子版ISSN：1804-0462
出版年度：2016
卷号：106
期号：1
页码：159-168
DOI：10.1515/pralin-2016-0015
语种：English
出版社：Walter de Gruyter GmbH
摘要：We present Otedama, a fast, open-source tool for rule-based syntactic pre-ordering, a well established technique in statistical machine translation. Otedama implements both a learner for pre-ordering rules, as well as a component for applying these rules to parsed sentences. Our system is compatible with several external parsers and capable of accommodating many source and all target languages in any machine translation paradigm which uses parallel training data. We demonstrate improvements on a patent translation task over a state-of-the-art English-Japanese hierarchical phrase-based machine translation system. We compare Otedama with an existing syntax-based pre-ordering system, showing comparable translation performance at a runtime speedup of a factor of 4.5-10.