@inproceedings{jaisy-2026-metaswarm,
    title = "{M}eta{S}warm at {A}bjad{M}ed: Forensic Optimization and Class-Balanced Discovery for Medical Diglossia in Abjad Scripts",
    author = "Jaisy, Rahul",
    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-1.21/",
    pages = "144--148",
    abstract = "The classification of diglossic medical text presents a high-dimensional challenge defined by extreme class imbalance (N = 82) and the orthographic ambiguity of unvocalized Abjad scripts. While standard supervised learning often collapses into majority-class prediction due to the ``Long Tail'' distribution, we intro- duce a Human-in-the-Loop Forensic Opti- mization framework. Unlike static end-to-end pipelines, our approach decouples strategic hy- perparameter tuning from high-throughput tac- tical execution (Elastic Compute). We lever- age a rigorous Class-Balanced Focal Loss (CBFL) derived from the ``Effective Number of Samples'' theory (En) to stabilize the de- cision manifold against stochastic class domi- nance. Using a CAMELBERT-DA backbone optimized via a custom weighted trainer on Dual H200 GPUs, our system achieved a ro- bust Public Leaderboard score of 0.3588. We further perform a ``Linguistic Error Topology'' analysis, utilizing UMAP projections and atten- tion saliency, to demonstrate that generalization gaps are driven by dialectal ``Constraint Drift'' rather than stochastic model failure."
}