Building a graphetic dictionary for Japanese kanji: character look up based on brush strokes or stroke groups, and the display of kanji as path data

Authors:
Ulrich Apel;Julien Quint
Affiliations:
National Institute of Informatics, Hitotsubashi, Chiyoda-ku, Tokyo, Japan;National Institute of Informatics, Hitotsubashi, Chiyoda-ku, Tokyo, Japan
Venue:
ElectricDict '04 Proceedings of the Workshop on Enhancing and Using Electronic Dictionaries
Year:
2004

Citing 0
Cited 2

Orthographic similarity search for dictionary lookup of Japanese words

Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
Modelling the orthographic neighbourhood for japanese kanji

ICCPOL'06 Proceedings of the 21st international conference on Computer Processing of Oriental Languages: beyond the orient: the research challenges ahead

Quantified Score

Hi-index	0.00

Visualization

Abstract

Reading and writing Japanese isn't easy for Japanese and foreigners alike. While Japanese learn these skills at school, foreigners should be helped by good teaching material and dictionaries. Kanji lexica have to be very different from other dictionaries. Unfortunately existing lexica normally expect that the users already have a lot of information on a character to look it up---the character's stroke count, its radical or its pronunciation. Beginners normally don't have such information. This project creates data to allow for easier and more flexible look up of Japanese characters and to build better teaching material. It develops different approaches to make use of this data.