Paper: Stem Translation with Affix-Based Rule Selection for Agglutinative Languages

ACL ID P13-2065
Title Stem Translation with Affix-Based Rule Selection for Agglutinative Languages
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

Current translation models are mainly de- signed for languages with limited mor- phology, which are not readily applicable to agglutinative languages as the differ- ence in the way lexical forms are gener- ated. In this paper, we propose a nov- el approach for translating agglutinative languages by treating stems and affixes differently. We employ stem as the atomic translation unit to alleviate data spare- ness. In addition, we associate each stem- granularity translation rule with a distri- bution of related affixes, and select desir- able rules according to the similarity of their affix distributions with given spans to be translated. Experimental results show that our approach significantly improves the translation performance on tasks of translating from three Turkic languages to Chin...