@inproceedings{zhou-etal-2022-flipda,
    title = "{F}lip{DA}: Effective and Robust Data Augmentation for Few-Shot Learning",
    author = "Zhou, Jing  and
      Zheng, Yanan  and
      Tang, Jie  and
      Jian, Li  and
      Yang, Zhilin",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.acl-long.592/",
    doi = "10.18653/v1/2022.acl-long.592",
    pages = "8646--8665",
    abstract = "Most previous methods for text data augmentation are limited to simple tasks and weak baselines. We explore data augmentation on hard tasks (i.e., few-shot natural language understanding) and strong baselines (i.e., pretrained models with over one billion parameters). Under this setting, we reproduced a large number of previous augmentation methods and found that these methods bring marginal gains at best and sometimes degrade the performance much. To address this challenge, we propose a novel data augmentation method FlipDA that jointly uses a generative model and a classifier to generate label-flipped data. Central to the idea of FlipDA is the discovery that generating label-flipped data is more crucial to the performance than generating label-preserved data. Experiments show that FlipDA achieves a good tradeoff between effectiveness and robustness{---}it substantially improves many tasks while not negatively affecting the others."
}