Improving the Robustness of Deep Reading Comprehension Models by Leveraging Syntax Prior

Bowen Wu, Haoyang Huang, Zongsheng Wang, Qihang Feng, Jingsong Yu, Baoxun Wang


Abstract
Despite the remarkable progress on Machine Reading Comprehension (MRC) with the help of open-source datasets, recent studies indicate that most of the current MRC systems unfortunately suffer from weak robustness against adversarial samples. To address this issue, we attempt to take sentence syntax as the leverage in the answer predicting process which previously only takes account of phrase-level semantics. Furthermore, to better utilize the sentence syntax and improve the robustness, we propose a Syntactic Leveraging Network, which is designed to deal with adversarial samples by exploiting the syntactic elements of a question. The experiment results indicate that our method is promising for improving the generalization and robustness of MRC models against the influence of adversarial samples, with performance well-maintained.
Anthology ID:
D19-5807
Volume:
Proceedings of the 2nd Workshop on Machine Reading for Question Answering
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Adam Fisch, Alon Talmor, Robin Jia, Minjoon Seo, Eunsol Choi, Danqi Chen
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
53–57
Language:
URL:
https://aclanthology.org/D19-5807
DOI:
10.18653/v1/D19-5807
Bibkey:
Cite (ACL):
Bowen Wu, Haoyang Huang, Zongsheng Wang, Qihang Feng, Jingsong Yu, and Baoxun Wang. 2019. Improving the Robustness of Deep Reading Comprehension Models by Leveraging Syntax Prior. In Proceedings of the 2nd Workshop on Machine Reading for Question Answering, pages 53–57, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Improving the Robustness of Deep Reading Comprehension Models by Leveraging Syntax Prior (Wu et al., 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-5807.pdf