Japanese-Chinese Phrase Alignment Exploiting Shared Chinese Characters

要旨

Common Chinese characters between Japan-ese and Chinese have been proved to be effective in Japanese-Chinese phrase align-ment. Besides common Chinese characters, Japanese and Chinese also share many oth-er semantically equivalent Chinese characters. However, there are no available resources for this kind of Chinese characters. In this paper, we propose a statistical method aiming to de-tect these Chinese characters which we call s-tatistically equivalent Chinese characters. We exploit statistically equivalent Chinese charac-ters together with common Chinese characters in a joint phrase alignment model. Experimen-tal results show that our approach achieves over 1 point lower AER and 1 BLEU increase comparing to the baseline system. 1

主題