A Topic-Triggered Translation Model for Statistical Machine Translation

被引:0
作者
SU Jinsong [1 ,2 ]
WANG Zhihao [3 ]
WU Qingqiang [1 ]
YAO Junfeng [1 ]
LONG Fei [1 ]
ZHANG Haiying [1 ]
机构
[1] Software School, Xiamen University
[2] Provincial Key Laboratory for Computer Information Processing Technology, Soochow University
[3] Automation Department, Xiamen University
关键词
Statistical machine translation; Topictriggered translation model; Topical context information;
D O I
暂无
中图分类号
H085 [机器翻译];
学科分类号
050211 ;
摘要
Translation model containing translation rules with probabilities plays a crucial role in statistical machine translation. Conventional method estimates translation probabilities with only the consideration of cooccurrence frequencies of bilingual translation units, while ignoring document-level context information. In this paper, we extend the conventional translation model to a topic-triggered one. Specifically, we estimate topic-specific translation probabilities of translation rules by leveraging topical context information, and online score selected translation rules according to topic posterior distributions of translated sentences. As compared with the conventional model, our model allows for more fine-grained distinction among different translations. Experiment results on large data set demonstrate the effectiveness of our model.
引用
收藏
页码:65 / 72
页数:8
相关论文
共 6 条
[1]  
Bilingual LSA-based adaptation for statistical machine translation[J] . Yik-Cheung Tam,Ian Lane,Tanja Schultz.Machine Translation . 2008 (4)
[2]   Hierarchical phrase-based translation [J].
Chiang, David .
COMPUTATIONAL LINGUISTICS, 2007, 33 (02) :201-228
[3]   The alignment template approach to statistical machine translation [J].
Och, FJ ;
Ney, H .
COMPUTATIONAL LINGUISTICS, 2004, 30 (04) :417-449
[4]  
Minimum Error Rate Training in Statistical Machine Translation .2 Franz Josef Och. Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics . 2003
[5]  
MixtureModel Adaptation for SMT .2 Foster George,Roland Kuhn. 2thWorkshop on Statistical Machine Translation . 2007
[6]  
http://www.ldc.upenn.edu .