Journal: Annual Meeting of the Association for Computational Linguistics
Programming languages: Python
Project website: https://github.com/GT-SALT/MixText
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.