@inproceedings{zhang-etal-2022-complicate,
    title = "Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification",
    author = "Zhang, Xu  and
      Liu, Zejie  and
      Xiang, Yanzheng  and
      Zhou, Deyu",
    editor = "Calzolari, Nicoletta  and
      Huang, Chu-Ren  and
      Kim, Hansaem  and
      Pustejovsky, James  and
      Wanner, Leo  and
      Choi, Key-Sun  and
      Ryu, Pum-Mo  and
      Chen, Hsin-Hsi  and
      Donatelli, Lucia  and
      Ji, Heng  and
      Kurohashi, Sadao  and
      Paggio, Patrizia  and
      Xue, Nianwen  and
      Kim, Seokhwan  and
      Hahm, Younggyun  and
      He, Zhong  and
      Lee, Tony Kyungil  and
      Santus, Enrico  and
      Bond, Francis  and
      Na, Seung-Hoon",
    booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.coling-1.97/",
    pages = "1136--1145",
    abstract = "With the development of pre-trained models (PTMs), the performance of text classification has been continuously improved by directly employing the features generated by PTMs. However such way might not fully explore the knowledge in PTMs as it is constrained by the difficulty of the task. Compared to difficult task, the learning algorithms tend to saturate early on the simple task. Moreover, the native sentence representations derived from BERT are prone to be collapsed and directly employing such representation for text classification might fail to fully capture discriminative features. In order to address these issues, in this paper we propose a novel framework for text classification which implements a two-stage training strategy. In the pre-training stage, auxiliary labels are introduced to increase the task difficulties and to fully exploit the knowledge in the pre-trained model. In the fine-tuning stage, the textual representation learned in the pre-training stage is employed and the classifier is fine-tuned to obtain better classification performance. Experiments were conducted on six text classification corpora and the results showed that the proposed framework outperformed several state-of-the-art baselines."
}