Presentation 2015-06-05
Methods for Selecting Keywords and Calculating Similarities of Documents for Extracting Relationship of Meeting Minutes Generated by Speech Recognition.
Motoki Ito, Seikoh Nishita,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) There was a study of a technique to extract relationship of minutes generated by speech recognition system using collective entity resolution. This technique assumes that its input data, meeting minutes, include error words caused by mis-recognition of the system. The empirical evaluation in this earlier study found that the technique did not work fine. This paper describes improvement of the technique by refining two steps in the technique, keyword extraction and similarity calculation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Speech recognition / meeting minutes / text mining / entity resolution
Paper # TL2015-9,NLC2015-9
Date of Issue 2015-05-28 (TL, NLC)

Conference Information
Committee NLC / TL
Conference Date 2015/6/4(2days)
Place (in Japanese) (See Japanese page)
Place (in English) The University of Tokushima
Topics (in Japanese) (See Japanese page)
Topics (in English) Application of natural language proessing and linguistic analysis, and general topic of NLP
Chair Koichi Takeuchi(Okayama Univ.) / Tadahisa Kondo(Kogakuin Univ.)
Vice Chair Hiroshi Kanayama(IBM) / Makoto Ichise(NTT DoCoMo) / Chiaki Kubomura(Yamano College of Aesthetics) / Masami Suzuki(KDDI R&D Labs.)
Secretary Hiroshi Kanayama(Univ. of Tokyo/Hottolink) / Makoto Ichise(Ryukoku Univ.) / Chiaki Kubomura(Univ. of Tsukuba) / Masami Suzuki(Kyorin Univ.)
Assistant Kazutaka Shimada(Kyushu Inst. of Tech.) / Ryuichiro Higashinaka(NTT) / Eiji Tomida(Ehime Univ.) / Yasushi Tsubota(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Natural Language Understanding and Models of Communication / Technical Committee on Thought and Language
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Methods for Selecting Keywords and Calculating Similarities of Documents for Extracting Relationship of Meeting Minutes Generated by Speech Recognition.
Sub Title (in English)
Keyword(1) Speech recognition
Keyword(2) meeting minutes
Keyword(3) text mining
Keyword(4) entity resolution
1st Author's Name Motoki Ito
1st Author's Affiliation Takushoku University(Takushoku Univ.)
2nd Author's Name Seikoh Nishita
2nd Author's Affiliation Takushoku University(Takushoku Univ.)
Date 2015-06-05
Paper # TL2015-9,NLC2015-9
Volume (vol) vol.115
Number (no) TL-69,NLC-70
Page pp.pp.49-54(TL), pp.49-54(NLC),
#Pages 6
Date of Issue 2015-05-28 (TL, NLC)