Presentation 1997/7/24
A Hybrid Approach for Measuring Word Similarity
Atsushi Fujii, Takenobu Tokunaga, Hozumi Tanaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a new approach for word similarity measurement. The statistics-based computation of word similarity has been popular in recent research, but is associated with a significant computational cost. On the other hand, the use of hand-crafted thesauri as semantic resources is simple to implement, but lacks mathematical rigor. To integrate the advantages of these two approaches, we aim at calculating a statistical weight for each branch of a thesaurus, so that we can measure word similarity simply based on the length of the path between two words in the thesaurus. Our experiment on Japanese nouns shows that this framework upheld the inequality of statistics-based word similarity with an accuracy of more than 70%. We also report on the effectivity of our framework in the task of word sense disambiguation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) word similarity / thesaurus / statistical model / word sense disambiguation / corpus
Paper # NLC97-15
Date of Issue

Conference Information
Committee NLC
Conference Date 1997/7/24(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Hybrid Approach for Measuring Word Similarity
Sub Title (in English)
Keyword(1) word similarity
Keyword(2) thesaurus
Keyword(3) statistical model
Keyword(4) word sense disambiguation
Keyword(5) corpus
1st Author's Name Atsushi Fujii
1st Author's Affiliation Department of Computer Science Tokyo Institute of Technology()
2nd Author's Name Takenobu Tokunaga
2nd Author's Affiliation Department of Computer Science Tokyo Institute of Technology
3rd Author's Name Hozumi Tanaka
3rd Author's Affiliation Department of Computer Science Tokyo Institute of Technology
Date 1997/7/24
Paper # NLC97-15
Volume (vol) vol.97
Number (no) 199
Page pp.pp.-
#Pages 6
Date of Issue