Skip to content
/ R-AT Public

EMNLP 2022: "R-AT: Regularized Adversarial Training for Natural Language Understanding"

License

Notifications You must be signed in to change notification settings

IKMLab/R-AT

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

R-AT: Regularized Adversarial Training for Natural Language Understanding

Currently, adversarial training has become a popular and powerful regularization method in the natural language domain. In this paper, we propose Regularized Adversarial Training based on adversarial training and dropout, called R-AT, which forces the output probability distributions of different sub-models generated by dropout to be consistent with each other under the same adversarial sample input. Specifically, we generate adversarial samples by perturbing the word embeddings. For each adversarial sample fed to the model, R-AT minimizes both the adversarial risk and the bidirectional KL-divergence between the adversarial output distributions of two sub-models sampled by dropout. Through extensive experiments on 13 public natural language understanding datasets, we found that R-AT has improvements for many models (e.g., rnn-based, cnn-based, and transformer-based models). For the GLUE benchmark, when R-AT is only applied to the fine-tuning stage, it is able to improve the overall test score of the BERT-base model from 78.3 to 79.6 and the RoBERTa-large model from 88.1 to 88.6. Theoretical analysis reveals that R-AT has potential gradient regularization during the training process. Furthermore, R-AT can reduce the inconsistency between training and testing of models with dropout.

image

Citation

@inproceedings{ni2022R-AT,
  title={R-AT: Regularized Adversarial Training for Natural Language Understanding},
  author={Ni, Shiwen and Li, Jiawen and Kao, Hung-Yu},
  booktitle={Findings of the Association for Computational Linguistics: EMNLP 2022},
  year={2022}
}

Continuing to update...

About

EMNLP 2022: "R-AT: Regularized Adversarial Training for Natural Language Understanding"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages