This is the code for our long paper:
Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model
Accepted to Findings of ACL 2022.
The source code will be complete before May 2022.
Download counter-fitted-vectors.txt and then put it in '/src/TextFooler/'.
Download USE and then put it in '/src/TextFooler/'.