BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks

Yannik Keller, Jan Mackensen, Steffen Eger


Anthology ID:
2021.findings-acl.141
Volume:
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1616–1629
Language:
URL:
https://aclanthology.org/2021.findings-acl.141
DOI:
10.18653/v1/2021.findings-acl.141
Bibkey:
Cite (ACL):
Yannik Keller, Jan Mackensen, and Steffen Eger. 2021. BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1616–1629, Online. Association for Computational Linguistics.
Cite (Informal):
BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks (Keller et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-acl.141.pdf
Video:
 https://aclanthology.org/2021.findings-acl.141.mp4
Code
 yannikkellerde/BERT-Defense
Data
GLUE