Presentation 2007/7/17
Extracting String Features with Adaptation for Text Classification
Katsuhiro Hirata, Masayuki Okabe, Kyoji Umemura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In traditional methods for text classification, words are used as a set of features for a document However there are many string-based approaches In the string-based approaches, the number of all substrings of documents would be extremely large and we don't know which substring is important for text classification. Previous research reports that using conditional probabilities based on mutual information for extracting features is effective We reports extracting features with adaptation and that the method is more useful for text classification
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Text Classification / Feature Extraction / Suffix Tree / Support Vector Machine
Paper # NLC2007-21
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) Extracting String Features with Adaptation for Text Classification
Sub Title (in English)
Keyword(1) Text Classification
Keyword(2) Feature Extraction
Keyword(3) Suffix Tree
Keyword(4) Support Vector Machine
1st Author's Name Katsuhiro Hirata
1st Author's Affiliation Information & Computer Sciences, Toyohashi University of Technology()
2nd Author's Name Masayuki Okabe
2nd Author's Affiliation Information and Media Center, Toyohashi University of Technology
3rd Author's Name Kyoji Umemura
3rd Author's Affiliation Information & Computer Sciences, Toyohashi University of Technology
Date 2007/7/17
Paper # NLC2007-21
Volume (vol) vol.107
Number (no) 158
Page pp.pp.-
#Pages 6
Date of Issue