计算机与数字工程2017，Vol.45Issue(12)：2389-2392,2427,5.DOI:10.3969/j.issn.1672-9722.2017.12.014
词汇化调序模型中融合语言特性的层次短语翻译方法研究∗
A Lexicalized Reordering Model of Integrating with Language Features for Hierarchical Phrase-based Translation
张阳 1余正涛 2周珂1
作者信息
- 1. 昆明理工大学信息科学与自动化学院 昆明 650500
- 2. 昆明理工大学智能信息处理重点实验室 昆明650500
- 折叠
摘要
Abstract
According to the language characteristics of Vietnamese,this paper proposed a new lexicalized reordering model where language features were integrated for Chinese-Vietnamese statistical machine translation.Firstly,the grammar differences be?tween Chinese and Vietnamese were analyzed,and the sequence differences in attribute,adverbial modifier and adjuncts were ex?tracted.Secondly,the extracted difference rulers were formally defined and be integrated in the lexicalized reordering model via the log-linear model.In the training processing,the proposed model would optimize the weight for these rules that conform to the lin?guistic features Finally,it would guide the translation selection in the decoding. The experiment had verified that our reordering model achieved a 0.6-2.1 BLEU point improvements for Chinese-to-Vietnamese translation over a baseline hierarchical phrase-based system.关键词
统计机器翻译/词汇化调序模型/汉语/越南语/语言特性Key words
statistical machine translation/lexicalized reordering model/chinese/vietnamese/language features分类
信息技术与安全科学引用本文复制引用
张阳,余正涛,周珂..词汇化调序模型中融合语言特性的层次短语翻译方法研究∗[J].计算机与数字工程,2017,45(12):2389-2392,2427,5.
