TY - GEN
T1 - Combining knowledge hunting and neural language models to solve the Winograd schema challenge
AU - Prakash, Ashok
AU - Sharma, Arpit
AU - Mitra, Arindam
AU - Baral, Chitta
N1 - Funding Information:
Support from DARPA and NSF grant 1816039 is acknowledged.
Publisher Copyright:
© 2019 Association for Computational Linguistics
PY - 2020
Y1 - 2020
N2 - Winograd Schema Challenge (WSC) is a pronoun resolution task which seems to require reasoning with commonsense knowledge. The needed knowledge is not present in the given text. Automatic extraction of the needed knowledge is a bottleneck in solving the challenge. The existing state-of-the-art approach uses the knowledge embedded in their pre-trained language model. However, the language models only embed part of the knowledge, the ones related to frequently co-existing concepts. This limits the performance of such models on the WSC problems. In this work, we build-up on the language model based methods and augment them with a commonsense knowledge hunting (using automatic extraction from text) module and an explicit reasoning module. Our end-to-end system built in such a manner improves on the accuracy of two of the available language model based approaches by 5.53% and 7.7% respectively. Overall our system achieves the state-of-the-art accuracy of 71.06% on the WSC dataset, an improvement of 7.36% over the previous best.
AB - Winograd Schema Challenge (WSC) is a pronoun resolution task which seems to require reasoning with commonsense knowledge. The needed knowledge is not present in the given text. Automatic extraction of the needed knowledge is a bottleneck in solving the challenge. The existing state-of-the-art approach uses the knowledge embedded in their pre-trained language model. However, the language models only embed part of the knowledge, the ones related to frequently co-existing concepts. This limits the performance of such models on the WSC problems. In this work, we build-up on the language model based methods and augment them with a commonsense knowledge hunting (using automatic extraction from text) module and an explicit reasoning module. Our end-to-end system built in such a manner improves on the accuracy of two of the available language model based approaches by 5.53% and 7.7% respectively. Overall our system achieves the state-of-the-art accuracy of 71.06% on the WSC dataset, an improvement of 7.36% over the previous best.
UR - http://www.scopus.com/inward/record.url?scp=85084086606&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084086606&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084086606
T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
SP - 6110
EP - 6119
BT - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
Y2 - 28 July 2019 through 2 August 2019
ER -