@inproceedings{bernier-colborne-etal-2019-improving,
    title = "Improving Cuneiform Language Identification with {BERT}",
    author = "Bernier-Colborne, Gabriel  and
      Goutte, Cyril  and
      L{\'e}ger, Serge",
    editor = {Zampieri, Marcos  and
      Nakov, Preslav  and
      Malmasi, Shervin  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Tiedemann, J{\"o}rg  and
      Ali, Ahmed},
    booktitle = "Proceedings of the Sixth Workshop on {NLP} for Similar Languages, Varieties and Dialects",
    month = jun,
    year = "2019",
    address = "Ann Arbor, Michigan",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W19-1402",
    doi = "10.18653/v1/W19-1402",
    pages = "17--25",
    abstract = "We describe the systems developed by the National Research Council Canada for the Cuneiform Language Identification (CLI) shared task at the 2019 VarDial evaluation campaign. We compare a state-of-the-art baseline relying on character n-grams and a traditional statistical classifier, a voting ensemble of classifiers, and a deep learning approach using a Transformer network. We describe how these systems were trained, and analyze the impact of some preprocessing and model estimation decisions. The deep neural network achieved 77{\%} accuracy on the test data, which turned out to be the best performance at the CLI evaluation, establishing a new state-of-the-art for cuneiform language identification.",
}