@inproceedings{bayrak-issifu-2022-domain,
    title = "Domain-Adapted {BERT}-based Models for Nuanced {A}rabic Dialect Identification and Tweet Sentiment Analysis",
    author = "Bayrak, Giyaseddin  and
      Issifu, Abdul Majeed",
    editor = "Bouamor, Houda  and
      Al-Khalifa, Hend  and
      Darwish, Kareem  and
      Rambow, Owen  and
      Bougares, Fethi  and
      Abdelali, Ahmed  and
      Tomeh, Nadi  and
      Khalifa, Salam  and
      Zaghouani, Wajdi",
    booktitle = "Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.wanlp-1.43/",
    doi = "10.18653/v1/2022.wanlp-1.43",
    pages = "425--430",
    abstract = "This paper summarizes the solution of the Nuanced Arabic Dialect Identification (NADI) 2022 shared task. It consists of two subtasks: a country-level Arabic Dialect Identification (ADID) and an Arabic Sentiment Analysis (ASA). Our work shows the importance of using domain-adapted models and language-specific pre-processing in NLP task solutions. We implement a simple but strong baseline technique to increase the stability of fine-tuning settings to obtain a good generalization of models. Our best model for the Dialect Identification subtask achieves a Macro F-1 score of 25.54{\%} as an average of both Test-A (33.89{\%}) and Test-B (19.19{\%}) F-1 scores. We also obtained a Macro F-1 score of 74.29{\%} of positive and negative sentiments only, in the Sentiment Analysis task."
}