@inproceedings{li-etal-2021-cascadebert-accelerating,
    title = "{C}ascade{BERT}: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade",
    author = "Li, Lei  and
      Lin, Yankai  and
      Chen, Deli  and
      Ren, Shuhuai  and
      Li, Peng  and
      Zhou, Jie  and
      Sun, Xu",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.findings-emnlp.43/",
    doi = "10.18653/v1/2021.findings-emnlp.43",
    pages = "475--486"
}