Presentation 2017-06-02
Taxonomy Classification By Explicit Semantic Analysis & Deep Machine Learning
Kento Hayasaka, Incheon Paik,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Text classification by machine learning is an important and popular research topic. Classification of texts between different domains has shown very good performance, but similar texts, for example, concepts with taxonomies under the same ontological origin, are more difficult to be classified by the existing approaches. In this research, to improve taxonomical text classification, we use an additional concept with Explicit Semantic Analysis (ESA) and apply it to the existing shallow learning such as Support Vector Machine (SVM) and deep Convolutional Neural Network(CNN). We could get a good improvement of about 5% using ESA and CNN.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Taxonomy ClassificationSemantic AnalysisConvolutional Neural NetworkSVMClustering
Paper # SC2017-3
Date of Issue 2017-05-26 (SC)

Conference Information
Committee SC
Conference Date 2017/6/2(2days)
Place (in Japanese) (See Japanese page)
Place (in English) University of Aizu(UBIC 3D)
Topics (in Japanese) (See Japanese page)
Topics (in English) Service Computing including IoT, Big Data Analytics, Intelligent Communication System, and Other Issues
Chair Incheon Paik(Univ. of Aizu)
Vice Chair Masahide Nakamura(Kobe Univ.)
Secretary Masahide Nakamura(NICT)
Assistant

Paper Information
Registration To Technical Committee on Service Computing
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Taxonomy Classification By Explicit Semantic Analysis & Deep Machine Learning
Sub Title (in English)
Keyword(1) Taxonomy ClassificationSemantic AnalysisConvolutional Neural NetworkSVMClustering
1st Author's Name Kento Hayasaka
1st Author's Affiliation University of Aizu(Univ. of Aizu)
2nd Author's Name Incheon Paik
2nd Author's Affiliation University of Aizu(Univ. of Aizu)
Date 2017-06-02
Paper # SC2017-3
Volume (vol) vol.117
Number (no) SC-75
Page pp.pp.11-15(SC),
#Pages 5
Date of Issue 2017-05-26 (SC)