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 proceedingConference contribution

5 Scopus citations

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 languageEnglish (US)
Title of host publicationLogical Formalizations of Commonsense Reasoning - Papers from the AAAI Spring Symposium, Technical Report
PublisherAI Access Foundation
Pages141-144
Number of pages4
VolumeSS-15-04
ISBN (Electronic)9781577357087
StatePublished - 2015
Event2015 AAAI Spring Symposium - Palo Alto, United States
Duration: Mar 23 2015Mar 25 2015

Other

Other2015 AAAI Spring Symposium
CountryUnited States
CityPalo Alto
Period3/23/153/25/15

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Sharma, A., Vo, N. H., Gaur, S., & Baral, C. (2015). An approach to solve winograd schema challenge using automatically extracted commonsense knowledge. In Logical Formalizations of Commonsense Reasoning - Papers from the AAAI Spring Symposium, Technical Report (Vol. SS-15-04, pp. 141-144). AI Access Foundation.