@inproceedings{goutte-leger-2016-advances,
    title = "Advances in Ngram-based Discrimination of Similar Languages",
    author = "Goutte, Cyril  and
      L{\'e}ger, Serge",
    editor = {Nakov, Preslav  and
      Zampieri, Marcos  and
      Tan, Liling  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Tiedemann, J{\"o}rg  and
      Malmasi, Shervin},
    booktitle = "Proceedings of the Third Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial3)",
    month = dec,
    year = "2016",
    address = "Osaka, Japan",
    publisher = "The COLING 2016 Organizing Committee",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W16-4823/",
    pages = "178--184",
    abstract = "We describe the systems entered by the National Research Council in the 2016 shared task on discriminating similar languages. Like previous years, we relied on character ngram features, and a mixture of discriminative and generative statistical classifiers. We mostly investigated the influence of the amount of data on the performance, in the open task, and compared the two-stage approach (predicting language/group, then variant) to a flat approach. Results suggest that ngrams are still state-of-the-art for language and variant identification, and that additional data has a small but decisive impact."
}