Presentation 1998/12/10
Deep Case Acquisition System by Dialogue with Users
Yoshiyuki MASATOMI, Kenji ARAKI, Koji TOCHINAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In natural language processing, case frams are treated as essential in expressing the meaning of sentences. Deep cases expressing semantic relation between a verb and its case are important for the analysis of sentences. In the case of use deep cases for semantic analysis, it is an important problem that they have ambiguity. Each user has various classifications of deep cases. We acquire deep cases by dialogue with users to resolve user's ambiguity. In this report, we propose the deep case acquisition method by dialogue. Then, we carry out the experiment for evaluating the system based on our method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deep case / User's ambiguity / Dialogue / Semantic analysis
Paper # NLC98-35,SP98-99
Date of Issue

Conference Information
Committee NLC
Conference Date 1998/12/10(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) Deep Case Acquisition System by Dialogue with Users
Sub Title (in English)
Keyword(1) Deep case
Keyword(2) User's ambiguity
Keyword(3) Dialogue
Keyword(4) Semantic analysis
1st Author's Name Yoshiyuki MASATOMI
1st Author's Affiliation Graduate School of Engineering, Hokkaido University()
2nd Author's Name Kenji ARAKI
2nd Author's Affiliation Graduate School of Engineering, Hokkaido University
3rd Author's Name Koji TOCHINAI
3rd Author's Affiliation Graduate School of Engineering, Hokkaido University
Date 1998/12/10
Paper # NLC98-35,SP98-99
Volume (vol) vol.98
Number (no) 460
Page pp.pp.-
#Pages 8
Date of Issue