Generating 'A for Alpha' When There Are Thousands of Characters

摘要

The phonetic alphabet enables people to dictate letters of the alphabet accurately by using representative words, i.e., A for Alpha. Japanese kanji (idiographic Chinese characters) vastly outnumber the letters of the Roman alphabet, and thus Japanese requires an explanatory reading like a phonetic alphabet. We call the explanatory reading of a kanji a "distinctive explanation." Most kanji characters have their homophones, and the role of the distinctive explanations is to enable users to identify a specific kanji character only by listening to the explanation. In this paper, we propose a corpus-based method for automatically generating distinctive explanations for a kanji, in which information about familiarity and homophones of kanji are taken into consideration. Through the kanji-identification experiments, we show that the quality of the explanations generated by the proposed method is higher than that of the manually crafted distinctive explanations.