Paper: Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information

ACL ID P12-1048
Title Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

To adapt a translation model trained from the data in one domain to another, previous works paid more attention to the studies of parallel corpus while ignoring the in-domain monolingual corpora which can be obtained more easily. In this paper, we propose a novel approach for translation model adapta- tion by utilizing in-domain monolingual top- ic information instead of the in-domain bilin- gual corpora, which incorporates the topic in- formation into translation probability estima- tion. Our method establishes the relationship between the out-of-domain bilingual corpus and the in-domain monolingual corpora vi- a topic mapping and phrase-topic distribution probability estimation from in-domain mono- lingual corpora. Experimental result on the NIST Chinese-English translation task shows th...