@misc{wang2020minilmv,
  title={MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers},
  author={Wenhui Wang and Hangbo Bao and Shaohan Huang and Li Dong and Furu Wei},
  year={2020},
  eprint={2012.15828},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2012.15828}
}