Presentation 2007/7/17
Collection of example sentences according to the meaning of a word and estimation of the number of meanings by using semi-supervised clustering
Hiroyuki Shinnou, Minoru Sasaki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a semi-supervised clustering method to collect sentences according to the meaning of a word. In this task, the estimation of the cluster number is most important. Our method concentrates on this problem. First we overestimate the number of meaning (the cluster number) for the target word. By using the number, we conduct the general clustering for data set to get many small clusters. Next using constrains given by the user, we integrate clusters. Our method performs the high precision with small constrains. In the experiment, we try our method for 12 Japanese noun words used in the SENSEVAL2 Japanese dictionary task. The experiment shows the effectiveness of our method. In future, we will improve the measurement of the similarity of sentences.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) semi-supervised clustering / example sentences / number of meanings / similarity between sentences / SENSEVAL2 Japanese dictionary task
Paper # NLC2007-13
Date of Issue

Conference Information
Committee NLC
Conference Date 2007/7/17(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) Collection of example sentences according to the meaning of a word and estimation of the number of meanings by using semi-supervised clustering
Sub Title (in English)
Keyword(1) semi-supervised clustering
Keyword(2) example sentences
Keyword(3) number of meanings
Keyword(4) similarity between sentences
Keyword(5) SENSEVAL2 Japanese dictionary task
1st Author's Name Hiroyuki Shinnou
1st Author's Affiliation Department of Computer and Information Sciences, Ibaraki University()
2nd Author's Name Minoru Sasaki
2nd Author's Affiliation Department of Computer and Information Sciences, Ibaraki University
Date 2007/7/17
Paper # NLC2007-13
Volume (vol) vol.107
Number (no) 158
Page pp.pp.-
#Pages 6
Date of Issue