@inproceedings{rifat-dewan-2026-reignite,
title = "{REIGNITE} at {A}bjad{M}ed: Imbalance-Aware Fine-Tuning of Pretrained {A}rabic Transformers for {A}rabic Medical Text Classification Task",
author = "Rifat, Nahid Montasir and
Dewan, Foyez Ahmed",
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://aclanthology.org/2026.abjadnlp-1.19/",
pages = "132--136",
abstract = "This paper presents our system developed for the AbjadNLP Shared Task 4 on Medical Text Classification in Arabic, which aims to assign Arabic medical question-answer pairs to a predefined set of medical categories. The task poses significant challenges due to severe class imbalance across 82 categories and the linguistic complexity of domain-specific Arabic medical text. To address these challenges, we propose an imbalance-aware training framework that combines targeted data augmentation for minority classes with class-weighted focal loss during fine-tuning. We evaluate multiple Arabic pretrained transformer models under a unified training configuration and further improve robustness through a majority-voting ensemble of the best-performing models. Our approach achieves competitive performance, ranking 15th on the private leaderboard with a macro F1 score of 0.4052, demonstrating the effectiveness of combining different data augmentation techniques, imbalance-aware training objectives, and ensemble learning for large-scale, highly imbalanced Arabic medical text classification. The code is available on GitHub."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rifat-dewan-2026-reignite">
<titleInfo>
<title>REIGNITE at AbjadMed: Imbalance-Aware Fine-Tuning of Pretrained Arabic Transformers for Arabic Medical Text Classification Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nahid</namePart>
<namePart type="given">Montasir</namePart>
<namePart type="family">Rifat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Foyez</namePart>
<namePart type="given">Ahmed</namePart>
<namePart type="family">Dewan</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 presents our system developed for the AbjadNLP Shared Task 4 on Medical Text Classification in Arabic, which aims to assign Arabic medical question-answer pairs to a predefined set of medical categories. The task poses significant challenges due to severe class imbalance across 82 categories and the linguistic complexity of domain-specific Arabic medical text. To address these challenges, we propose an imbalance-aware training framework that combines targeted data augmentation for minority classes with class-weighted focal loss during fine-tuning. We evaluate multiple Arabic pretrained transformer models under a unified training configuration and further improve robustness through a majority-voting ensemble of the best-performing models. Our approach achieves competitive performance, ranking 15th on the private leaderboard with a macro F1 score of 0.4052, demonstrating the effectiveness of combining different data augmentation techniques, imbalance-aware training objectives, and ensemble learning for large-scale, highly imbalanced Arabic medical text classification. The code is available on GitHub.</abstract>
<identifier type="citekey">rifat-dewan-2026-reignite</identifier>
<location>
<url>https://aclanthology.org/2026.abjadnlp-1.19/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>132</start>
<end>136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T REIGNITE at AbjadMed: Imbalance-Aware Fine-Tuning of Pretrained Arabic Transformers for Arabic Medical Text Classification Task
%A Rifat, Nahid Montasir
%A Dewan, Foyez Ahmed
%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 rifat-dewan-2026-reignite
%X This paper presents our system developed for the AbjadNLP Shared Task 4 on Medical Text Classification in Arabic, which aims to assign Arabic medical question-answer pairs to a predefined set of medical categories. The task poses significant challenges due to severe class imbalance across 82 categories and the linguistic complexity of domain-specific Arabic medical text. To address these challenges, we propose an imbalance-aware training framework that combines targeted data augmentation for minority classes with class-weighted focal loss during fine-tuning. We evaluate multiple Arabic pretrained transformer models under a unified training configuration and further improve robustness through a majority-voting ensemble of the best-performing models. Our approach achieves competitive performance, ranking 15th on the private leaderboard with a macro F1 score of 0.4052, demonstrating the effectiveness of combining different data augmentation techniques, imbalance-aware training objectives, and ensemble learning for large-scale, highly imbalanced Arabic medical text classification. The code is available on GitHub.
%U https://aclanthology.org/2026.abjadnlp-1.19/
%P 132-136
Markdown (Informal)
[REIGNITE at AbjadMed: Imbalance-Aware Fine-Tuning of Pretrained Arabic Transformers for Arabic Medical Text Classification Task](https://aclanthology.org/2026.abjadnlp-1.19/) (Rifat & Dewan, AbjadNLP 2026)
ACL