Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks
Xing Wu, Chaochen Gao, Meng Lin, Liangjun Zang, Songlin Hu
Abstract
Before entering the neural network, a token is generally converted to the corresponding onehot representation, which is a discrete distribution of the vocabulary. Smoothed representation is the probability of candidate tokens obtained from a pre-trained masked language model, which can be seen as a more informative substitution to the one-hot representation. We propose an efficient data augmentation method, termed text smoothing, by converting a sentence from its one-hot representation to a controllable smoothed representation. We evaluate text smoothing on different benchmarks in a low-resource regime. Experimental results show that text smoothing outperforms various mainstream data augmentation methods by a substantial margin. Moreover, text smoothing can be combined with those data augmentation methods to achieve better performance. Our code are available at https://github.com/caskcsg/TextSmoothing.