Presentation 2012-08-31
Feature Words that Describe Problem Sentence in Scientific Article
Toshihiko SAKAI, Sachio HIROKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The literature survey on related work requires a lot of efforts in reading all articles that are retrieved by queries. We have to understand the contents from several view points, such as the problem and the method that the articles describe. Search from these viewpoints will improve the efficiency of survey, if particular segments of articles were extracted, indexed and can be used as auxiliary query. This paper focuses on the sentence that describes the problem in an abstract and the feature sets that describe such problem sentences. Discernment performance are evaluated by 10-fold cross-validation for six candidates of feature sets. It turned out that the set of all words gains the best performance if 90% of the data are used as a training data. However, the set of a small number of words with positive scores outperforms other feature sets, if the training data is only 10%. In such a realistic situation, the feature words are effective in improving discernment.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Feature Words / SVM / Cross validation / Scientific Article
Paper # NLC2012-23
Date of Issue

Conference Information
Committee NLC
Conference Date 2012/8/23(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) Feature Words that Describe Problem Sentence in Scientific Article
Sub Title (in English)
Keyword(1) Feature Words
Keyword(2) SVM
Keyword(3) Cross validation
Keyword(4) Scientific Article
1st Author's Name Toshihiko SAKAI
1st Author's Affiliation Kyushu University()
2nd Author's Name Sachio HIROKAWA
2nd Author's Affiliation Kyushu University
Date 2012-08-31
Paper # NLC2012-23
Volume (vol) vol.112
Number (no) 196
Page pp.pp.-
#Pages 6
Date of Issue