@inproceedings{gaanoun-benelallam-2020-arabic,
    title = "{A}rabic dialect identification: An {A}rabic-{BERT} model with data augmentation and ensembling strategy",
    author = "Gaanoun, Kamel  and
      Benelallam, Imade",
    editor = "Zitouni, Imed  and
      Abdul-Mageed, Muhammad  and
      Bouamor, Houda  and
      Bougares, Fethi  and
      El-Haj, Mahmoud  and
      Tomeh, Nadi  and
      Zaghouani, Wajdi",
    booktitle = "Proceedings of the Fifth Arabic Natural Language Processing Workshop",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.wanlp-1.28/",
    pages = "275--281",
    abstract = "This paper presents the ArabicProcessors team`s deep learning system designed for the NADI 2020 Subtask 1 (country-level dialect identification) and Subtask 2 (province-level dialect identification). We used Arabic-Bert in combination with data augmentation and ensembling methods. Unlabeled data provided by task organizers (10 Million tweets) was split into multiple subparts, to which we applied semi-supervised learning method, and finally ran a specific ensembling process on the resulting models. This system ranked 3rd in Subtask 1 with 23.26{\%} F1-score and 2nd in Subtask 2 with 5.75{\%} F1-score."
}