@inproceedings{le-2026-kvochurhegel,
    title = "{K}vochur{H}egel at {A}bjad{M}ed: Combining {LDAM} Loss and Adversarial Training for {A}rabic Medical Question-Answer Classification",
    author = "Le, Minh-Hoang",
    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-1.16/",
    pages = "120--123",
    abstract = "This paper describes our team{'}s submission to AbjadMed at AbjadNLP 2026. The task involves classifying Arabic medical question-answer pairs into 82 categories, characterized by a long-tail distribution and significant semantic overlap. While domain-specific Arabic models exist, they are primarily optimized for Named Entity Recognition or span-extraction tasks rather than high-cardinality sequence classification. Consequently, our system adopts a robust optimization approach using a general-purpose encoder. We utilize ARBERTv2 as the backbone, employing Label-Distribution-Aware Margin (LDAM) loss to mitigate class imbalance and Fast Gradient Method (FGM) adversarial training to enhance generalization boundaries. Our approach achieves a Macro-F1 score of 0.4028 on the private test set, demonstrating that advanced optimization techniques can yield competitive performance on specialized taxonomies without requiring domain-specific pre-training."
}