Presentation 1993/12/10
A Semi-Automatic Construction of Kanji Thesaurus from Existing Thesauruses
Kazumi Kawamura, Masahiro Miyazaki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Japanese sentences contain many words written by kanji characters.A kanji character is originally ideogram,and means a basic concept by oneself.Whereas two kanji string,which constructs most of nouns in Japanese,means a compound concept.In two kanji string,one kanji character modifies another(main noun).From this point of view,we propose kanji thesaurus which represents various relations between kanji characters.It is applied to describe the meaning of noun word and to extract facets automatically for multi- demensional thesaurus which can represent various relations between words.This paper shows necessary informations for noun, verb and adjective kanji thesaurus and a semi-automatic construction method of kanji thesaurus from existing thesauruses.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) natural language processing / thesaurus / kanji character / two kanji string
Paper # NLC93-59
Date of Issue

Conference Information
Committee NLC
Conference Date 1993/12/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Semi-Automatic Construction of Kanji Thesaurus from Existing Thesauruses
Sub Title (in English)
Keyword(1) natural language processing
Keyword(2) thesaurus
Keyword(3) kanji character
Keyword(4) two kanji string
1st Author's Name Kazumi Kawamura
1st Author's Affiliation The Graduated School of Engineering,Niigata University()
2nd Author's Name Masahiro Miyazaki
2nd Author's Affiliation The Graduated School of Engineering,Niigata University
Date 1993/12/10
Paper # NLC93-59
Volume (vol) vol.93
Number (no) 367
Page pp.pp.-
#Pages 8
Date of Issue