@inproceedings{bogoychev-etal-2022-edinburghs,
    title = "{E}dinburgh{'}s Submission to the {WMT} 2022 Efficiency Task",
    author = "Bogoychev, Nikolay  and
      Behnke, Maximiliana  and
      Van Der Linde, Jelmer  and
      Nail, Graeme  and
      Heafield, Kenneth  and
      Zhang, Biao  and
      Kashyap, Sidharth",
    booktitle = "Proceedings of the Seventh Conference on Machine Translation (WMT)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.wmt-1.63",
    pages = "661--667",
    abstract = "We participated in all tracks of the WMT 2022 efficient machine translation task: single-core CPU, multi-core CPU, and GPU hardware with throughput and latency conditions. Our submissions explores a number of several efficiency strategies: knowledge distillation, a simpler simple recurrent unit (SSRU) decoder with one or two layers, shortlisting, deep encoder, shallow decoder, pruning and bidirectional decoder. For the CPU track, we used quantized 8-bit models. For the GPU track, we used FP16 quantisation. We explored various pruning strategies and combination of one or more of the above methods.",
}