Training Tips for the Transformer Model

Martin Popel, Ondrej Bojar. Training Tips for the Transformer Model. Prague Bull. Math. Linguistics, 110:43-70, 2018. [doi]

@article{PopelB18,
  title = {Training Tips for the Transformer Model},
  author = {Martin Popel and Ondrej Bojar},
  year = {2018},
  url = {http://ufal.mff.cuni.cz/pbml/110/art-popel-bojar.pdf},
  researchr = {https://researchr.org/publication/PopelB18},
  cites = {0},
  citedby = {0},
  journal = {Prague Bull. Math. Linguistics},
  volume = {110},
  pages = {43-70},
}