Presentation 2017-02-09
Recognizing Textual Entailment with Dependency-Parsed Structure Taking into Account Copular Sentence
Akira Saito, Koichi Takeuchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the previous study of recognizing textual entailment, content word matching based approaches are often applied into recognizing entailments. However, in the methods that do not take into account the order of the content words appearing in the sentences, not small number of sentence pairs would be wrongly judged as entailed. In this paper, thus we propose an approach to recognize entailments by detecting the inclusive relation with text structures. The Predicate-Argument Structure Analyzer (ASA) was used to generate the sentence structure from the natural language sentences. In conventional ASA analysis, classification of content words and function words was inadequate for predicates in copula sentences. Thus, the ASA was improved on this point and the evaluation experiment was conducted using the RITE2 problem set provided in NTCIR-10. As the results of the evaluation experiments, we report that three cases of successful recognition of entailments by the improvement of ASA.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Recognizing Textual Entailments / Predicate Argument Structure / Copular Sentence
Paper # NLC2016-40
Date of Issue 2017-02-02 (NLC)

Conference Information
Committee NLC / IPSJ-IFAT
Conference Date 2017/2/9(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Hiroshi Kanayama(IBM)
Vice Chair Makoto Ichise(NTT DoCoMo) / Takeshi Sakaki(Univ. of Tokyo/Hottolink)
Secretary Makoto Ichise(Ryukoku Univ.) / Takeshi Sakaki(Kyushu Inst. of Tech.)
Assistant Ryuichiro Higashinaka(NTT) / Mitsuo Yoshida(Toyohashi Univ. of Tech.)

Paper Information
Registration To Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Information Fundamentals and Access Technologies
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Recognizing Textual Entailment with Dependency-Parsed Structure Taking into Account Copular Sentence
Sub Title (in English)
Keyword(1) Recognizing Textual Entailments
Keyword(2) Predicate Argument Structure
Keyword(3) Copular Sentence
1st Author's Name Akira Saito
1st Author's Affiliation Okayama University(Okayama Univ.)
2nd Author's Name Koichi Takeuchi
2nd Author's Affiliation Okayama University(Okayama Univ.)
Date 2017-02-09
Paper # NLC2016-40
Volume (vol) vol.116
Number (no) NLC-451
Page pp.pp.1-5(NLC),
#Pages 5
Date of Issue 2017-02-02 (NLC)