@inproceedings{snissarenko-2026-olga,
    title = "Olga Snissarenko at {A}bjad{M}ed: {A}rabic Clinical Text Classification with {A}ra{BERT}: Results from the {A}bjad{M}ed Shared Task",
    author = "Snissarenko, Olga",
    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-1.25/",
    pages = "177--181",
    abstract = "We present a solution for the Arabic medical text classification task, formulated as a multi-class classification problem with 82 medical categories. The task is challenging due to severe class imbalance, long and heterogeneous input texts, and the presence of domain-specific medical terminology in Modern Standard Arabic. Our approach is based on fine-tuning pretrained AraBERT models with a focus on loss-level imbalance handling rather than architectural complexity. Through a systematic comparison of multiple AraBERT-based configurations, we show that class-weighted loss combined with simple mean pooling yields the strongest performance. Our best model achieves a macro-F1 score of 0.387 on the public evaluation set and 0.411 on the private test set."
}