Presentation 2006-02-03
Self-refinement Method of Concept Base Based on Recurrent Enhancing of Attribute
Junya MURAKAMI, Hirokazu WATABE, Tsukasa KAWAOKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) To associate the concept more accurately, the refinement of the Concept-Base is one of the most important factors. The present Concept-Base is mechanically constructed with the dictionary and the newspaper. It is composed by about 30 attributes on the average concept. When the number of attributes of concepts is little, the related level calculation becomes inaccurate. Then, it proposes the method to attempt the improvement of the quality of the Concept-Base by adding the word selected by using the degree of association.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Concept-Base / Degree of Association / Attribute / Refinement
Paper # NLC2005-125
Date of Issue

Conference Information
Committee NLC
Conference Date 2006/1/27(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) Self-refinement Method of Concept Base Based on Recurrent Enhancing of Attribute
Sub Title (in English)
Keyword(1) Concept-Base
Keyword(2) Degree of Association
Keyword(3) Attribute
Keyword(4) Refinement
1st Author's Name Junya MURAKAMI
1st Author's Affiliation Department of Knowledge Engineering and Computer Sciences, Doshisha University()
2nd Author's Name Hirokazu WATABE
2nd Author's Affiliation Department of Knowledge Engineering and Computer Sciences, Doshisha University
3rd Author's Name Tsukasa KAWAOKA
3rd Author's Affiliation Department of Knowledge Engineering and Computer Sciences, Doshisha University
Date 2006-02-03
Paper # NLC2005-125
Volume (vol) vol.105
Number (no) 595
Page pp.pp.-
#Pages 6
Date of Issue