Modeling impression in probabilistic transliteration into Chinese

Abstract

For transliterating foreign words into Chinese, the pronunciation of a source word is spelled out with Kanji characters. Because Kanji comprises ideograms, an individual pronunciation may be represented by more than one character. However, because different Kanji characters convey different meanings and impressions, characters must be selected carefully. In this paper, we propose a transliteration method that models both pronunciation and impression, whereas existing methods do not model impression. Given a source word and impression keywords related to the source word, our method derives possible transliteration candidates and sorts them according to their probability. We evaluate our method experimentally. © 2006 Association for Computational Linguistics.