@inproceedings{wang-etal-2022-huawei,
    title = "Huawei {B}abel{T}ar {NMT} at {WMT}22 Biomedical Translation Task: How We Further Improve Domain-specific {NMT}",
    author = "Wang, Weixuan  and
      Meng, Xupeng  and
      Yan, Suqing  and
      Tian, Ye  and
      Peng, Wei",
    editor = {Koehn, Philipp  and
      Barrault, Lo{\"i}c  and
      Bojar, Ond{\v{r}}ej  and
      Bougares, Fethi  and
      Chatterjee, Rajen  and
      Costa-juss{\`a}, Marta R.  and
      Federmann, Christian  and
      Fishel, Mark  and
      Fraser, Alexander  and
      Freitag, Markus  and
      Graham, Yvette  and
      Grundkiewicz, Roman  and
      Guzman, Paco  and
      Haddow, Barry  and
      Huck, Matthias  and
      Jimeno Yepes, Antonio  and
      Kocmi, Tom  and
      Martins, Andr{\'e}  and
      Morishita, Makoto  and
      Monz, Christof  and
      Nagata, Masaaki  and
      Nakazawa, Toshiaki  and
      Negri, Matteo  and
      N{\'e}v{\'e}ol, Aur{\'e}lie  and
      Neves, Mariana  and
      Popel, Martin  and
      Turchi, Marco  and
      Zampieri, Marcos},
    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://preview.aclanthology.org/add-emnlp-2024-awards/2022.wmt-1.87/",
    pages = "930--935",
    abstract = "This paper describes Huawei Artificial Intelligence Application Research Center`s neural machine translation system ({\textquotedblleft}BabelTar{\textquotedblright}). Our submission to the WMT22 biomedical translation shared task covers language directions between English and the other seven languages (French, German, Italian, Spanish, Portuguese, Russian, and Chinese). During the past four years, our participation in this domain-specific track has witnessed a paradigm shift of methodology from a purely data-driven focus to embracing diversified techniques, including pre-trained multilingual NMT models, homograph disambiguation, ensemble learning, and preprocessing methods. We illustrate practical insights and measured performance improvements relating to how we further improve our domain-specific NMT system."
}