@misc{nguyen2019transformers,
  title={Transformers without Tears: Improving the Normalization of Self-Attention},
  author={Toan Q. Nguyen and Julian Salazar},
  year={2019},
  eprint={1910.05895},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  doi={10.5281/zenodo.3525484},
  url={https://arxiv.org/abs/1910.05895}
}