Presentation 2006-07-28
Analysis on Manual Identification of Inter-sentential Discourse Relation
Manami SAITO, Kazuhide YAMAMOTO, Satoshi SEKINE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We aim to make a system which identifies a discourse relation between sentences automatically. We previously proposed a method which identifies the discourse relation between two successive sentences using statistics given by a huge corpus, and the accuracy was 65%. In this paper, in order to improve the accuracy, we observe human identification results of this task. Three subjects identify the discourse relation by two ways: one uses whole text, the other uses only two sentences. Our observation shows the relationship for each discourse relation in visually. Moreover, relevance of the relationship was explored with comparing the result of SVM.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) discourse relations / manual identification / SVM
Paper # NLC2006-12
Date of Issue

Conference Information
Committee NLC
Conference Date 2006/7/21(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) Analysis on Manual Identification of Inter-sentential Discourse Relation
Sub Title (in English)
Keyword(1) discourse relations
Keyword(2) manual identification
Keyword(3) SVM
1st Author's Name Manami SAITO
1st Author's Affiliation Nagaoka University of Technology()
2nd Author's Name Kazuhide YAMAMOTO
2nd Author's Affiliation Nagaoka University of Technology
3rd Author's Name Satoshi SEKINE
3rd Author's Affiliation New York University
Date 2006-07-28
Paper # NLC2006-12
Volume (vol) vol.106
Number (no) 191
Page pp.pp.-
#Pages 6
Date of Issue