Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment 论文

2020Proceedings of the AAAI Conference on Artificial Intelligence引用 857
DOIPDF
Adversarial Robustness in Machine LearningTopic Modeling
人工智能Topic ModelingAdversarial Robustness in Machine Learning
相关技术:Topic ModelingAdversarial Robustness in Machine Learning
关系图谱

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment · 作者

D

Di Jin

P

Peter Szolovits

J

Joey Tianyi Zhou

Z

Zhijing Jin