Japanese-chinese phrase alignment using common chinese characters information

We describe a method to detect common Chi-nese characters between Japanese and Chi-nese automatically by means of freely avail-able resources and verify the effectiveness of the detecting method. We use a joint phrase alignment model on dependency trees and re-port results of experiments aimed at improv-ing the alignment quality between Japanese and Chinese by incorporating the common Chinese characters information detected by proposed detecting method into the alignmen-t model. Experimental results of Japanese-Chinese phrase alignment show that our ap-proach could achieve 0.73 points lower AER than the baseline system.