Presentation 2005/7/16
A Proposition of a Method for Deep Case Analysis Based on Activity in Network
Hideyuki SHIBUKI, Kenji ARAKI, Yoshio MOMOUCHI, Koji TOCHINAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a method for analyzing deep case of a noun in a different sentence from a sentence in which a verb is. The method is an application of our previous method [2], [3] to context analysis. The previous method is based on the assumption that each word concept has deep case preference, which is the tendency of interpretaion of the word as a specific deep case. Analysis using the deep case preference can be performed without a word order and a grammatical word. We attempt to analyze a deep case of a word, which is recognized by keyword spotting, based on the preference. Then an output is determinated using the activity of a node corresponding the word. In this paper, we report the framework of the method and a result of preliminary experiment.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) context analysis / deep case / anaphora / network / activity
Paper # NLC2005-15
Date of Issue

Conference Information
Committee NLC
Conference Date 2005/7/16(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) A Proposition of a Method for Deep Case Analysis Based on Activity in Network
Sub Title (in English)
Keyword(1) context analysis
Keyword(2) deep case
Keyword(3) anaphora
Keyword(4) network
Keyword(5) activity
1st Author's Name Hideyuki SHIBUKI
1st Author's Affiliation Graduate School of Business Administration, Hokkai-Gakuen University:High-Tech Research Center, Hokkai-Gakuen University()
2nd Author's Name Kenji ARAKI
2nd Author's Affiliation Graduate School of Information Science and Technology, Hokkaido University
3rd Author's Name Yoshio MOMOUCHI
3rd Author's Affiliation Faculty of Engineering, Hokkai-Gakuen University:High-Tech Research Center, Hokkai-Gakuen University
4th Author's Name Koji TOCHINAI
4th Author's Affiliation Faculty of Business Administration, Hokkai-Gakuen University
Date 2005/7/16
Paper # NLC2005-15
Volume (vol) vol.105
Number (no) 204
Page pp.pp.-
#Pages 6
Date of Issue