@inproceedings{malmasi-etal-2016-discriminating,
    title = "Discriminating between Similar Languages and {A}rabic Dialect Identification: A Report on the Third {DSL} Shared Task",
    author = {Malmasi, Shervin  and
      Zampieri, Marcos  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Nakov, Preslav  and
      Ali, Ahmed  and
      Tiedemann, J{\"o}rg},
    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://aclanthology.org/W16-4801",
    pages = "1--14",
    abstract = "We present the results of the third edition of the Discriminating between Similar Languages (DSL) shared task, which was organized as part of the VarDial{'}2016 workshop at COLING{'}2016. The challenge offered two subtasks: subtask 1 focused on the identification of very similar languages and language varieties in newswire texts, whereas subtask 2 dealt with Arabic dialect identification in speech transcripts. A total of 37 teams registered to participate in the task, 24 teams submitted test results, and 20 teams also wrote system description papers. High-order character n-grams were the most successful feature, and the best classification approaches included traditional supervised learning methods such as SVM, logistic regression, and language models, while deep learning approaches did not perform very well.",
}