@inproceedings{oumar-mrini-2022-ahmed,
    title = "Ahmed and Khalil at {NADI} 2022: Transfer Learning and Addressing Class Imbalance for {A}rabic Dialect Identification and Sentiment Analysis",
    author = "Oumar, Ahmed  and
      Mrini, Khalil",
    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-1.46/",
    doi = "10.18653/v1/2022.wanlp-1.46",
    pages = "442--446",
    abstract = "In this paper, we present our findings in the two subtasks of the 2022 NADI shared task. First, in the Arabic dialect identification subtask, we find that there is heavy class imbalance, and propose to address this issue using focal loss. Our experiments with the focusing hyperparameter confirm that focal loss improves performance. Second, in the Arabic tweet sentiment analysis subtask, we deal with a smaller dataset, where text includes both Arabic dialects and Modern Standard Arabic. We propose to use transfer learning from both pre-trained MSA language models and our own model from the first subtask. Our system ranks in the 5th and 7th best spots of the leaderboards of first and second subtasks respectively."
}