This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amount of augmented training samples by interpolating text in hidden space. Moreover, we leverage recent advances in data augmentation to guess low-entropy labels for unlabeled data, hence making them as easy to use as labeled data.By mixing labeled, unlabeled and augmented data, MixText significantly outperformed current pre-trained and fined-tuned models and other state-of-the-art semi-supervised learning methods on several text classification benchmarks. The improvement is especially prominent when supervision is extremely limited. We have publicly released our code at https://github.com/GT-SALT/MixText.
@article{arxiv.2004.12239,
title = {MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification},
author = {Jiaao Chen and Zichao Yang and Diyi Yang},
journal= {arXiv preprint arXiv:2004.12239},
year = {2020}
}