@article{li-etal-2021-differentiable, title = "Differentiable Subset Pruning of Transformer Heads", author = "Li, Jiaoda and Cotterell, Ryan and Sachan, Mrinmaya", 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/jlcl-multiple-ingestion/2021.tacl-1.86/", doi = "10.1162/tacl_a_00436", pages = "1442--1459" }