@article{efficientcontentbasedsparseattentionwith,
  title = {Efficient Content-Based Sparse Attention with Routing Transformers},
  author = {Aurko Roy and Mohammad Saffar and Ashish Vaswani and David Grangier},
  year = {2020},
  eprint = {2003.05997},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2003.05997v5},
}