@inproceedings{aji-heafield-2019-making,
    title = "Making Asynchronous Stochastic Gradient Descent Work for Transformers",
    author = "Aji, Alham Fikri  and
      Heafield, Kenneth",
    editor = "Birch, Alexandra  and
      Finch, Andrew  and
      Hayashi, Hiroaki  and
      Konstas, Ioannis  and
      Luong, Thang  and
      Neubig, Graham  and
      Oda, Yusuke  and
      Sudoh, Katsuhito",
    booktitle = "Proceedings of the 3rd Workshop on Neural Generation and Translation",
    month = nov,
    year = "2019",
    address = "Hong Kong",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D19-5608/",
    doi = "10.18653/v1/D19-5608",
    pages = "80--89"
}