@inproceedings{shanshin-2026-arabicmedicalbert,
    title = "{A}rabic{M}edical{BERT}-{QA}-82 at {A}bjad{M}ed: Fighting Class Imbalance in {A}rabic Medical Text Classification",
    author = "Shanshin, Gleb",
    booktitle = "Proceedings of the 2nd Workshop on {NLP} for Languages Using {A}rabic Script",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.abjadnlp-1.15/",
    pages = "115--119",
    abstract = "We present a supervised system for Arabic medical question-answer classification developed for the AbjadMed shared task. The task involves assigning one of 82 highly imbalanced medical categories and is evaluated using macro-averaged F1. Our approach builds on an AraBERT model further pretrained on a related Arabic medical classification dataset. Under a unified fine-tuning setup, this domain-adapted model consistently outperforms general-purpose Arabic backbones, with the best results obtained using a low backbone learning rate, indicating that only limited adaptation is required. The final system achieves a macro F1 score of 0.51 on the private test split. For comparison, we evaluate several cost-efficient large language models under constrained prompting and observe substantially lower performance."
}