@article{ganesh-etal-2021-compressing, title = "Compressing Large-Scale Transformer-Based Models: A Case Study on {BERT}", author = "Ganesh, Prakhar and Chen, Yao and Lou, Xin and Khan, Mohammad Ali and Yang, Yin and Sajjad, Hassan and Nakov, Preslav and Chen, Deming and Winslett, Marianne", editor = "Roark, Brian and Nenkova, Ani", journal = "Transactions of the Association for Computational Linguistics", volume = "9", year = "2021", address = "Cambridge, MA", publisher = "MIT Press", url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2021.tacl-1.63/", doi = "10.1162/tacl_a_00413", pages = "1061--1080" }