Clone wiki

pinyomi / Home



Pinyomi (拼読み) is a Chinese-Japanese dictionary system based on cognates and visually similar characters. Simplified Chinese characters (hanzi) and Japanese kanji characters are historically related, and both were derived originally from an earlier form of Chinese characters. Pinyomi makes use of the visual similarity between Chinese and Japanese to enable fast dictionary lookup based on guessed pronunciation.

Both Chinese and Japanese dictionaries are relatively slow to use if you do not know a word's pronunciation. Pinyomi allows a Chinese speaker to guess a pronunciation for a Japanese word and use that to find the word in the dictionary. Similarly for Japanese speakers trying to look up a Chinese word.

This system is a fully functional prototype, written in late 2006 by Zhihui Jin and Lars Yencken under the supervision of Kumiko Tanaka-Ishii. It was later superseded by Zhihui Jin's later rewrite, Pinyomi-Lite, which featured improved accessibility and performance compared to this system. It requires several data files to run, namely a dictionary of cognates, and corpus frequency counts for both Chinese and Japanese characters and words.

Related publications

  • Jin, Zhihui and Yencken, Lars and Tanaka-Ishii, Kumiko: "漢字対応に基づく日中辞書検索 (Japanese-Chinese dictionary lookup using ideogram transliteration)", in Proceedings of NLP 2007, Otsu, Shiga Japan (2007) pdf
  • Yencken, Lars and Jin, Zhihui and Tanaka-Ishii, Kumiko: "Pinyomi - Dictionary lookup via orthographic associations", in Proceedings of PACLING 2007, Melbourne, Australia (2007) pdf