Targeted Adversarial Training for Natural Language Understanding

04/12/2021
by   Lis Pereira, et al.
0

We present a simple yet effective Targeted Adversarial Training (TAT) algorithm to improve adversarial training for natural language understanding. The key idea is to introspect current mistakes and prioritize adversarial training steps to where the model errs the most. Experiments show that TAT can significantly improve accuracy over standard adversarial training on GLUE and attain new state-of-the-art zero-shot results on XNLI. Our code will be released at: https://github.com/namisan/mt-dnn.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset