IIT-KGP at COIN 2019: Using pre-trained Language Models for modeling Machine Comprehension

Prakhar Sharma, Sumegh Roychowdhury


Abstract
In this paper, we describe our system for COIN 2019 Shared Task 1: Commonsense Inference in Everyday Narrations. We show the power of leveraging state-of-the-art pre-trained language models such as BERT(Bidirectional Encoder Representations from Transformers) and XLNet over other Commonsense Knowledge Base Resources such as ConceptNet and NELL for modeling machine comprehension. We used an ensemble of BERT-Large and XLNet-Large. Experimental results show that our model give substantial improvements over the baseline and other systems incorporating knowledge bases. We bagged 2nd position on the final test set leaderboard with an accuracy of 90.5%
Anthology ID:
D19-6009
Volume:
Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Simon Ostermann, Sheng Zhang, Michael Roth, Peter Clark
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
80–84
Language:
URL:
https://aclanthology.org/D19-6009
DOI:
10.18653/v1/D19-6009
Bibkey:
Cite (ACL):
Prakhar Sharma and Sumegh Roychowdhury. 2019. IIT-KGP at COIN 2019: Using pre-trained Language Models for modeling Machine Comprehension. In Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing, pages 80–84, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
IIT-KGP at COIN 2019: Using pre-trained Language Models for modeling Machine Comprehension (Sharma & Roychowdhury, 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-6009.pdf