An approach to solve winograd schema challenge using automatically extracted commonsense knowledge

Arpit Sharma; Nguyen H. Vo; Shruti Gaur; Chitta Baral

An approach to solve winograd schema challenge using automatically extracted commonsense knowledge

Arpit Sharma, Nguyen H. Vo, Shruti Gaur, Chitta Baral

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The Winograd Schema Challenge has recently been proposed as an alternative to the Turing test. A Winograd Schema consists of a sentence and question pair such that the answer to the question depends on the resolution of a definite pronoun in the sentence. The answer is fairly intuitive for humans but is difficult for machines because it requires commonsense knowledge about words or concepts in the sentence. In this paper we propose a novel technique which semanti-cally parses the text, hunts for the needed commonsense knowledge and uses that knowledge to answer the given question.

Original language	English (US)
Title of host publication	Logical Formalizations of Commonsense Reasoning - Papers from the AAAI Spring Symposium, Technical Report
Publisher	AI Access Foundation
Pages	141-144
Number of pages	4
Volume	SS-15-04
ISBN (Electronic)	9781577357087
State	Published - 2015
Event	2015 AAAI Spring Symposium - Palo Alto, United States Duration: Mar 23 2015 → Mar 25 2015

Other

Other	2015 AAAI Spring Symposium
Country/Territory	United States
City	Palo Alto
Period	3/23/15 → 3/25/15

ASJC Scopus subject areas

Artificial Intelligence

Cite this

An approach to solve winograd schema challenge using automatically extracted commonsense knowledge. / Sharma, Arpit; Vo, Nguyen H.; Gaur, Shruti et al.
Logical Formalizations of Commonsense Reasoning - Papers from the AAAI Spring Symposium, Technical Report. Vol. SS-15-04 AI Access Foundation, 2015. p. 141-144.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

@inproceedings{b1bc6c7643f24b25a85fe5a32bb44f28,

title = "An approach to solve winograd schema challenge using automatically extracted commonsense knowledge",

abstract = "The Winograd Schema Challenge has recently been proposed as an alternative to the Turing test. A Winograd Schema consists of a sentence and question pair such that the answer to the question depends on the resolution of a definite pronoun in the sentence. The answer is fairly intuitive for humans but is difficult for machines because it requires commonsense knowledge about words or concepts in the sentence. In this paper we propose a novel technique which semanti-cally parses the text, hunts for the needed commonsense knowledge and uses that knowledge to answer the given question.",

author = "Arpit Sharma and Vo, {Nguyen H.} and Shruti Gaur and Chitta Baral",

year = "2015",

language = "English (US)",

volume = "SS-15-04",

pages = "141--144",

booktitle = "Logical Formalizations of Commonsense Reasoning - Papers from the AAAI Spring Symposium, Technical Report",

publisher = "AI Access Foundation",

note = "2015 AAAI Spring Symposium ; Conference date: 23-03-2015 Through 25-03-2015",

}

TY - GEN

T1 - An approach to solve winograd schema challenge using automatically extracted commonsense knowledge

AU - Sharma, Arpit

AU - Vo, Nguyen H.

AU - Gaur, Shruti

AU - Baral, Chitta

PY - 2015

Y1 - 2015

N2 - The Winograd Schema Challenge has recently been proposed as an alternative to the Turing test. A Winograd Schema consists of a sentence and question pair such that the answer to the question depends on the resolution of a definite pronoun in the sentence. The answer is fairly intuitive for humans but is difficult for machines because it requires commonsense knowledge about words or concepts in the sentence. In this paper we propose a novel technique which semanti-cally parses the text, hunts for the needed commonsense knowledge and uses that knowledge to answer the given question.

AB - The Winograd Schema Challenge has recently been proposed as an alternative to the Turing test. A Winograd Schema consists of a sentence and question pair such that the answer to the question depends on the resolution of a definite pronoun in the sentence. The answer is fairly intuitive for humans but is difficult for machines because it requires commonsense knowledge about words or concepts in the sentence. In this paper we propose a novel technique which semanti-cally parses the text, hunts for the needed commonsense knowledge and uses that knowledge to answer the given question.

UR - http://www.scopus.com/inward/record.url?scp=84986917852&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986917852&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84986917852

VL - SS-15-04

SP - 141

EP - 144

BT - Logical Formalizations of Commonsense Reasoning - Papers from the AAAI Spring Symposium, Technical Report

PB - AI Access Foundation

T2 - 2015 AAAI Spring Symposium

Y2 - 23 March 2015 through 25 March 2015

ER -

An approach to solve winograd schema challenge using automatically extracted commonsense knowledge

Abstract

Other

ASJC Scopus subject areas

Other files and links

Cite this