@inproceedings{singh-2026-medarabs,
    title = "{M}ed{A}rabs at {A}bjad{M}ed: {A}rabic Medical Text Classification via Data- and Algorithm-Level Fusion",
    author = "Singh, Amrita",
    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-1.12/",
    pages = "100--104",
    abstract = "In this work, we address the challenges of Arabic medical text classification, focusing on class imbalance and the complexity of the language{'}s morphology. We propose a multiclass classification pipeline based on Data- and Algorithm-Level fusion, which integrates the optimal Back Translation technique for data augmentation with the Class Balanced (CB) loss function to enhance performance. The domain-specific AraBERT model is fine-tuned using this approach, achieving competitive results. On the official test set of the AbjadMed task, our pipeline achieves a Macro-F1 score of 0.4219, and it achieves 0.4068 on the development set."
}