InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective

Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu. InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. [doi]

Authors

Boxin Wang

This author has not been identified. Look up 'Boxin Wang' in Google

Shuohang Wang

This author has not been identified. Look up 'Shuohang Wang' in Google

Yu Cheng

This author has not been identified. Look up 'Yu Cheng' in Google

Zhe Gan

This author has not been identified. Look up 'Zhe Gan' in Google

Ruoxi Jia

This author has not been identified. Look up 'Ruoxi Jia' in Google

Bo Li

This author has not been identified. Look up 'Bo Li' in Google

Jingjing Liu

This author has not been identified. Look up 'Jingjing Liu' in Google