Flipda: Effective And Robust Data Augmentation For Few-shot Learning
Jing Zhou, Yanan Zheng, Jie Tang, Jian Li, Zhilin Yang . Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 2022 – 48 citations
[Paper]
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.