Recognizing implicit discourse relations through abductive reasoning with large-scale lexical knowledge

Jun Sugiura; Naoya Inoue; Kentaro Inui

Recognizing implicit discourse relations through abductive reasoning with large-scale lexical knowledge

Jun Sugiura, Naoya Inoue, Kentaro Inui

INF - System Information Sciences

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

Discourse relation recognition is the task of identifying the semantic relationships between textual units. Conventional approaches to discourse relation recognition exploit surface information and syntactic information as machine learning features. However, the performance of these models is severely limited for implicit discourse relation recognition. In this paper, we propose an abductive theorem proving (ATP) approach for implicit discourse relation recognition. The contribution of this paper is that we give a detailed discussion of an ATP-based discourse relation recognition model with open-domain web texts.

Original language	English
Pages (from-to)	76-87
Number of pages	12
Journal	CEUR Workshop Proceedings
Volume	1044
Publication status	Published - 2013 Jan 1
Event	1st Workshop on Natural Language Processing and Automated Reasoning, NLPAR 2013 - Co-located with 12th International Conference on Logic Programming and Nonmonotonic Reasoning, LPNMR 2013 - A Corunna, Spain Duration: 2013 Sep 15 → …

Keywords

Abductive reasoning
Association information
Discourse relation
Lexical knowledge

ASJC Scopus subject areas

Computer Science(all)

Fingerprint Dive into the research topics of 'Recognizing implicit discourse relations through abductive reasoning with large-scale lexical knowledge'. Together they form a unique fingerprint.

Cite this

@article{f78e45db00c245bd8c9dd1370dfc62a3,

title = "Recognizing implicit discourse relations through abductive reasoning with large-scale lexical knowledge",

abstract = "Discourse relation recognition is the task of identifying the semantic relationships between textual units. Conventional approaches to discourse relation recognition exploit surface information and syntactic information as machine learning features. However, the performance of these models is severely limited for implicit discourse relation recognition. In this paper, we propose an abductive theorem proving (ATP) approach for implicit discourse relation recognition. The contribution of this paper is that we give a detailed discussion of an ATP-based discourse relation recognition model with open-domain web texts.",

keywords = "Abductive reasoning, Association information, Discourse relation, Lexical knowledge",

author = "Jun Sugiura and Naoya Inoue and Kentaro Inui",

year = "2013",

month = jan,

day = "1",

language = "English",

volume = "1044",

pages = "76--87",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

note = "1st Workshop on Natural Language Processing and Automated Reasoning, NLPAR 2013 - Co-located with 12th International Conference on Logic Programming and Nonmonotonic Reasoning, LPNMR 2013 ; Conference date: 15-09-2013",

}

TY - JOUR

T1 - Recognizing implicit discourse relations through abductive reasoning with large-scale lexical knowledge

AU - Sugiura, Jun

AU - Inoue, Naoya

AU - Inui, Kentaro

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Discourse relation recognition is the task of identifying the semantic relationships between textual units. Conventional approaches to discourse relation recognition exploit surface information and syntactic information as machine learning features. However, the performance of these models is severely limited for implicit discourse relation recognition. In this paper, we propose an abductive theorem proving (ATP) approach for implicit discourse relation recognition. The contribution of this paper is that we give a detailed discussion of an ATP-based discourse relation recognition model with open-domain web texts.

AB - Discourse relation recognition is the task of identifying the semantic relationships between textual units. Conventional approaches to discourse relation recognition exploit surface information and syntactic information as machine learning features. However, the performance of these models is severely limited for implicit discourse relation recognition. In this paper, we propose an abductive theorem proving (ATP) approach for implicit discourse relation recognition. The contribution of this paper is that we give a detailed discussion of an ATP-based discourse relation recognition model with open-domain web texts.

KW - Abductive reasoning

KW - Association information

KW - Discourse relation

KW - Lexical knowledge

UR - http://www.scopus.com/inward/record.url?scp=84924351975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924351975&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84924351975

VL - 1044

SP - 76

EP - 87

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

T2 - 1st Workshop on Natural Language Processing and Automated Reasoning, NLPAR 2013 - Co-located with 12th International Conference on Logic Programming and Nonmonotonic Reasoning, LPNMR 2013

Y2 - 15 September 2013

ER -

Recognizing implicit discourse relations through abductive reasoning with large-scale lexical knowledge

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Cite this