@inproceedings{NEURIPS2020_3f5ee243, author = {Wang, Wenhui and Wei, Furu and Dong, Li and Bao, Hangbo and Yang, Nan and Zhou, Ming}, booktitle = {Advances in Neural Information Processing Systems}, editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin}, pages = {5776--5788}, publisher = {Curran Associates, Inc.}, title = {MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers}, url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf}, volume = {33}, year = {2020} }