@inproceedings{scheduleddropheadaregularizationmethod,
  title = {Scheduled DropHead: A Regularization Method for Transformer Models},
  author = {Wangchunshu Zhou and Tao Ge and Ke Xu and Furu Wei and Ming Zhou},
  year = {2020},
  booktitle = {Findings of the Association for Computational Linguistics 2020},
  eprint = {2004.13342},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2004.13342v2},
}