@inproceedings{improvingdeeptransformerwithdepthscaled,
  title = {Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention},
  author = {Biao Zhang and Ivan Titov and Rico Sennrich},
  year = {2019},
  booktitle = {IJCNLP 2019 11},
  eprint = {1908.11365},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1908.11365v1},
}