@inproceedings{transformerdissectionanunified,
  title = {Transformer Dissection: A Unified Understanding of 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 = {EMNLP 2019 11},
  eprint = {1908.11775},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1908.11775v4},
}