Handling Japanese homophone errors in revision support system for Japanese texts: REVISE

Japanese texts frequently suffer from the homophone errors caused by the KANA-KANJI conversion needed to input the text. It is critical, therefore, for Japanese revision support systems to detect and to correct homophone errors. This paper proposes a method for detecting and correcting Japanese homophone errors in compound nouns. This method can not only detect Japanese homophone errors in compound nouns, but also can find the correct candidates for the detected errors automatically. Finding the correct candidates is one superiority of this method over existing methods. The basis idea of this method is that a compound noun component places some restrictions on the semantic categories of the adjoining words. The method accurately determines that a homophone is misused in a compound noun if one or both of its neighbors is not a member of the semantic set defined by the homophone. Also, the method successfully indicates the correct candidates for the detected homophone errors.