Presentation 2011-03-09
Consideration on Content Classification of Description Questionnaire Using Self-Organizing Map(1)
Takahiro TANAKA, Daiki HUZISAWA, Makoto OHOKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It takes huge time to analyze and summarize description questionair. And, different results are brought depending on the analyzer. This is also problem. Therefore, we are doing research on analyzing support of the description questionair on a computer. A word clustering which makes sets containing synonymous words, is required to execute before the sentence analyzing, as a primary process. In this report, we define a collocation probability vector based on lexical collocation probability appearing in the same sentence. We consider on a technique to apply the collocation probability vectors to SOM and a technique using correlation between the collocation probability vectors.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Network / Self-Organizing Map / Natural language processing
Paper # NC2010-196
Date of Issue

Conference Information
Committee NC
Conference Date 2011/2/28(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Consideration on Content Classification of Description Questionnaire Using Self-Organizing Map(1)
Sub Title (in English)
Keyword(1) Neural Network
Keyword(2) Self-Organizing Map
Keyword(3) Natural language processing
1st Author's Name Takahiro TANAKA
1st Author's Affiliation Faculty of Engineering, Tottori University()
2nd Author's Name Daiki HUZISAWA
2nd Author's Affiliation Faculty of Engineering, Tottori University
3rd Author's Name Makoto OHOKI
3rd Author's Affiliation Faculty of Engineering, Tottori University
Date 2011-03-09
Paper # NC2010-196
Volume (vol) vol.110
Number (no) 461
Page pp.pp.-
#Pages 4
Date of Issue