NAACL 2021long10 citations

Targeted Adversarial Training for Natural Language Understanding

Lis Pereira, Xiaodong Liu, Hao Cheng, Hoifung Poon, Jianfeng Gao, Ichiro Kobayashi

Abstract

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 upon acceptance of the paper.

BibTeX
@inproceedings{pereira-etal-2021-targeted,
    title = "Targeted Adversarial Training for Natural Language Understanding",
    author = "Pereira, Lis  and
      Liu, Xiaodong  and
      Cheng, Hao  and
      Poon, Hoifung  and
      Gao, Jianfeng  and
      Kobayashi, Ichiro",
    editor = "Toutanova, Kristina  and
      Rumshisky, Anna  and
      Zettlemoyer, Luke  and
      Hakkani-Tur, Dilek  and
      Beltagy, Iz  and
      Bethard, Steven  and
      Cotterell, Ryan  and
      Chakraborty, Tanmoy  and
      Zhou, Yichao",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.naacl-main.424/",
    doi = "10.18653/v1/2021.naacl-main.424",
    pages = "5385--5393"
}
Targeted Adversarial Training for Natural Language Understanding · NAACL 2021