CSReader at SemEval-2018 Task 11: Multiple Choice Question Answering as Textual Entailment

Zhengping Jiang, Qi Sun


Abstract
In this document we present an end-to-end machine reading comprehension system that solves multiple choice questions with a textual entailment perspective. Since some of the knowledge required is not explicitly mentioned in the text, we try to exploit commonsense knowledge by using pretrained word embeddings during contextual embeddings and by dynamically generating a weighted representation of related script knowledge. In the model two kinds of prediction structure are ensembled, and the final accuracy of our system is 10 percent higher than the naiive baseline.
Anthology ID:
S18-1176
Volume:
Proceedings of the 12th International Workshop on Semantic Evaluation
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marianna Apidianaki, Saif M. Mohammad, Jonathan May, Ekaterina Shutova, Steven Bethard, Marine Carpuat
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1053–1057
Language:
URL:
https://aclanthology.org/S18-1176
DOI:
10.18653/v1/S18-1176
Bibkey:
Cite (ACL):
Zhengping Jiang and Qi Sun. 2018. CSReader at SemEval-2018 Task 11: Multiple Choice Question Answering as Textual Entailment. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 1053–1057, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
CSReader at SemEval-2018 Task 11: Multiple Choice Question Answering as Textual Entailment (Jiang & Sun, SemEval 2018)
Copy Citation:
PDF:
https://aclanthology.org/S18-1176.pdf