@inproceedings{200210957,
  title = {MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers},
  author = {Wenhui Wang and Furu Wei and Li Dong and Hangbo Bao and Nan Yang and Ming Zhou},
  year = {2020},
  booktitle = {NeurIPS 2020 12},
  eprint = {2002.10957},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2002.10957v2},
}