@inproceedings{quinn-ballesteros-2018-pieces,
    title = "Pieces of Eight: 8-bit Neural Machine Translation",
    author = "Quinn, Jerry  and
      Ballesteros, Miguel",
    editor = "Bangalore, Srinivas  and
      Chu-Carroll, Jennifer  and
      Li, Yunyao",
    booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)",
    month = jun,
    year = "2018",
    address = "New Orleans - Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/N18-3014/",
    doi = "10.18653/v1/N18-3014",
    pages = "114--120",
    abstract = "Neural machine translation has achieved levels of fluency and adequacy that would have been surprising a short time ago. Output quality is extremely relevant for industry purposes, however it is equally important to produce results in the shortest time possible, mainly for latency-sensitive applications and to control cloud hosting costs. In this paper we show the effectiveness of translating with 8-bit quantization for models that have been trained using 32-bit floating point values. Results show that 8-bit translation makes a non-negligible impact in terms of speed with no degradation in accuracy and adequacy."
}