@article{erniesparselearninghierarchicalefficient,
  title = {ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention},
  author = {Yang Liu and Jiaxiang Liu and Li Chen and Yuxiang Lu and Shikun Feng and Zhida Feng and Yu Sun and Hao Tian and Hua Wu and Haifeng Wang},
  year = {2022},
  eprint = {2203.12276},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2203.12276v1},
}