@article{visualizingattentionintransformerbased,
  title = {Visualizing Attention in Transformer-Based Language Representation Models},
  author = {Jesse Vig},
  year = {2019},
  eprint = {1904.02679},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1904.02679v2},
}