@inproceedings{chen-etal-2020-mixtext,
    title = "{M}ix{T}ext: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification",
    author = "Chen, Jiaao  and
      Yang, Zichao  and
      Yang, Diyi",
    editor = "Jurafsky, Dan  and
      Chai, Joyce  and
      Schluter, Natalie  and
      Tetreault, Joel",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2020.acl-main.194/",
    doi = "10.18653/v1/2020.acl-main.194",
    pages = "2147--2157",
    abstract = "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 \url{https://github.com/GT-SALT/MixText}."
}