<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-2026-kvochurhegel">
    <titleInfo>
        <title>KvochurHegel at AbjadMed: Combining LDAM Loss and Adversarial Training for Arabic Medical Question-Answer Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Minh-Hoang</namePart>
        <namePart type="family">Le</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">le-2026-kvochurhegel</identifier>
    <location>
        <url>https://aclanthology.org/2026.abjadnlp-1.16/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>120</start>
            <end>123</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T KvochurHegel at AbjadMed: Combining LDAM Loss and Adversarial Training for Arabic Medical Question-Answer Classification
%A Le, Minh-Hoang
%S Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F le-2026-kvochurhegel
%X 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.
%U https://aclanthology.org/2026.abjadnlp-1.16/
%P 120-123

Markdown (Informal)

[KvochurHegel at AbjadMed: Combining LDAM Loss and Adversarial Training for Arabic Medical Question-Answer Classification](https://aclanthology.org/2026.abjadnlp-1.16/) (Le, AbjadNLP 2026)

• KvochurHegel at AbjadMed: Combining LDAM Loss and Adversarial Training for Arabic Medical Question-Answer Classification (Le, AbjadNLP 2026)

ACL

• Minh-Hoang Le. 2026. KvochurHegel at AbjadMed: Combining LDAM Loss and Adversarial Training for Arabic Medical Question-Answer Classification. In Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script, pages 120–123, Rabat, Morocco. Association for Computational Linguistics.