Presentation 2012-08-30
Clause Classification-based Retrieval of Demand Expressions from Local Assemblies Minutes
Fumitoshi ASHIHARA, Yasutomo KIMURA, Kenji ARAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we show how to estimate a verb that expresses a demand within a question to a city assemblyman in order to achieve an effective use of local assembly minutes which are available to the public on the Web. One of the problems of our task is that modality is not connected to a verb. Therefore, we apply clause-classification to solve this problem. Comparing with the baseline, experimental results show the effectiveness of our approach. It obtained 4.6 F-score increases with only modality and 9.3 F-score increases with modality and clause-classification.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) demand expression / modality / clause-classification
Paper # NLC2012-10
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) Clause Classification-based Retrieval of Demand Expressions from Local Assemblies Minutes
Sub Title (in English)
Keyword(1) demand expression
Keyword(2) modality
Keyword(3) clause-classification
1st Author's Name Fumitoshi ASHIHARA
1st Author's Affiliation Graduate School of information Science and Technology, Hokkaido University()
2nd Author's Name Yasutomo KIMURA
2nd Author's Affiliation Department of Information and Management Science, Otaru University Of Commerce
3rd Author's Name Kenji ARAKI
3rd Author's Affiliation Graduate School of information Science and Technology, Hokkaido University
Date 2012-08-30
Paper # NLC2012-10
Volume (vol) vol.112
Number (no) 196
Page pp.pp.-
#Pages 6
Date of Issue