Presentation 2019-11-28
Effectiveness of feature selection as pre-processing of LSTM using W2V
Shiori Koga, Tsunenori Mine, Sachio Hirokawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Among RNNs, especially LSTM is capable of long-term memory, and can be expected to acquire information including better contextual information, and has been used for various problems including classification problems. In such classification problems, various attempts have been made to improve the accuracy of classification by selecting features such as words that contribute to classification from among the words that make up sentences.However, since LSTM attaches importance to the context, no attempt has been made to select words in LSTM input as far as we know.In this study, we show the effectiveness of using Word2Vec as a word expression in an LSTM input sentence and performing feature selection as a pre-processing of the LSTM input. The results show that the accuracy of classification improves when feature selection is performed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) text classification / LSTM / feature selection / Word2Vec
Paper # AI2019-34
Date of Issue 2019-11-21 (AI)

Conference Information
Committee AI
Conference Date 2019/11/28(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Naoki Fukuta(Shizuoka Univ.)
Vice Chair Yuichi Sei(Univ. of Electro-Comm.) / Yuko Sakurai(AIST)
Secretary Yuichi Sei(Osaka Univ.) / Yuko Sakurai(Tokyo Univ. of Agriculture and Technology)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Effectiveness of feature selection as pre-processing of LSTM using W2V
Sub Title (in English)
Keyword(1) text classification
Keyword(2) LSTM
Keyword(3) feature selection
Keyword(4) Word2Vec
1st Author's Name Shiori Koga
1st Author's Affiliation Kyushu University(Kyushu Univ.)
2nd Author's Name Tsunenori Mine
2nd Author's Affiliation Kyushu University(Kyushu Univ.)
3rd Author's Name Sachio Hirokawa
3rd Author's Affiliation Research Institute for Information Technology, Kyushu University(Kyushu Univ.)
Date 2019-11-28
Paper # AI2019-34
Volume (vol) vol.119
Number (no) AI-317
Page pp.pp.25-30(AI),
#Pages 6
Date of Issue 2019-11-21 (AI)