Adversarial Word Dilution as Text Data Augmentation in Low-Resource Regime


  • Junfan Chen Beihang University
  • Richong Zhang Beihang University
  • Zheyan Luo Beihang University
  • Chunming Hu Beihang University
  • Yongyi Mao University of Ottawa



SNLP: Text Classification, SNLP: Adversarial Attacks & Robustness


Data augmentation is widely used in text classification, especially in the low-resource regime where a few examples for each class are available during training. Despite the success, generating data augmentations as hard positive examples that may increase their effectiveness is under-explored. This paper proposes an Adversarial Word Dilution (AWD) method that can generate hard positive examples as text data augmentations to train the low-resource text classification model efficiently. Our idea of augmenting the text data is to dilute the embedding of strong positive words by weighted mixing with unknown-word embedding, making the augmented inputs hard to be recognized as positive by the classification model. We adversarially learn the dilution weights through a constrained min-max optimization process with the guidance of the labels. Empirical studies on three benchmark datasets show that AWD can generate more effective data augmentations and outperform the state-of-the-art text data augmentation methods. The additional analysis demonstrates that the data augmentations generated by AWD are interpretable and can flexibly extend to new examples without further training.




How to Cite

Chen, J., Zhang, R., Luo, Z., Hu, C., & Mao, Y. (2023). Adversarial Word Dilution as Text Data Augmentation in Low-Resource Regime. Proceedings of the AAAI Conference on Artificial Intelligence, 37(11), 12626-12634.



AAAI Technical Track on Speech & Natural Language Processing