Open AccessA Topic‐Triggered Translation Model for Statistical Machine Translation
Author(s) -
Su Jinsong,
Wang Zhihao,
Wu Qingqiang,
Yao Junfeng,
Long Fei,
Zhang Haiying
Publication year - 2017
Publication title -
chinese journal of electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.267
H-Index - 25
eISSN - 2075-5597
pISSN - 1022-4653
DOI - 10.1049/cje.2016.10.007
Subject(s) - translation (biology) , computer science , machine translation , context (archaeology) , example based machine translation , natural language processing , artificial intelligence , set (abstract data type) , evaluation of machine translation , statistical model , machine translation software usability , machine learning , paleontology , biochemistry , chemistry , messenger rna , biology , gene , programming language
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.