@article{selfattentionattributioninterpreting,
  title = {Self-Attention Attribution: Interpreting Information Interactions Inside Transformer},
  author = {Yaru Hao and Li Dong and Furu Wei and Ke Xu},
  year = {2020},
  eprint = {2004.11207},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2004.11207v2},
}