@inproceedings{wadhawan-2021-dialect,
    title = "Dialect Identification in Nuanced {A}rabic Tweets Using Farasa Segmentation and {A}ra{BERT}",
    author = "Wadhawan, Anshul",
    editor = "Habash, Nizar  and
      Bouamor, Houda  and
      Hajj, Hazem  and
      Magdy, Walid  and
      Zaghouani, Wajdi  and
      Bougares, Fethi  and
      Tomeh, Nadi  and
      Abu Farha, Ibrahim  and
      Touileb, Samia",
    booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
    month = apr,
    year = "2021",
    address = "Kyiv, Ukraine (Virtual)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2021.wanlp-1.35/",
    pages = "291--295",
    abstract = "This paper presents our approach to address the EACL WANLP-2021 Shared Task 1: Nuanced Arabic Dialect Identification (NADI). The task is aimed at developing a system that identifies the geographical location(country/province) from where an Arabic tweet in the form of modern standard Arabic or dialect comes from. We solve the task in two parts. The first part involves pre-processing the provided dataset by cleaning, adding and segmenting various parts of the text. This is followed by carrying out experiments with different versions of two Transformer based models, AraBERT and AraELECTRA. Our final approach achieved macro F1-scores of 0.216, 0.235, 0.054, and 0.043 in the four subtasks, and we were ranked second in MSA identification subtasks and fourth in DA identification subtasks."
}