@inproceedings{transformerdissectionanunified1,
  title = {Transformer Dissection: An Unified Understanding for Transformer's Attention via the Lens of Kernel},
  author = {Yao-Hung Hubert Tsai and Shaojie Bai and Makoto Yamada and Louis-Philippe Morency and Ruslan Salakhutdinov},
  year = {2019},
  booktitle = {IJCNLP 2019 11},
  url = {https://aclanthology.org/D19-1443},
}