@inproceedings{yang-etal-2020-textbrewer,
    title = "{T}ext{B}rewer: {A}n {O}pen-{S}ource {K}nowledge {D}istillation {T}oolkit for {N}atural {L}anguage {P}rocessing",
    author = "Yang, Ziqing  and
      Cui, Yiming  and
      Chen, Zhipeng  and
      Che, Wanxiang  and
      Liu, Ting  and
      Wang, Shijin  and
      Hu, Guoping",
    editor = "Celikyilmaz, Asli  and
      Wen, Tsung-Hsien",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.acl-demos.2",
    doi = "10.18653/v1/2020.acl-demos.2",
    pages = "9--16",
    abstract = "In this paper, we introduce TextBrewer, an open-source knowledge distillation toolkit designed for natural language processing. It works with different neural network models and supports various kinds of supervised learning tasks, such as text classification, reading comprehension, sequence labeling. TextBrewer provides a simple and uniform workflow that enables quick setting up of distillation experiments with highly flexible configurations. It offers a set of predefined distillation methods and can be extended with custom code. As a case study, we use TextBrewer to distill BERT on several typical NLP tasks. With simple configurations, we achieve results that are comparable with or even higher than the public distilled BERT models with similar numbers of parameters.",
}