@inproceedings{emad-eldin-2026-tashkees,
title = "Tashkees-{AI} at {A}bjad{M}ed 2026: Flat vs. Hierarchical Classification for Fine-Grained {A}rabic Medical {QA}",
author = "Emad Eldin, Fatimah Mohamed",
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-1.20/",
pages = "137--143",
abstract = "This paper describes Tashkees-AI, a system developed for the AbjadMed 2026 Shared Task on Arabic Medical Question Classification. A comprehensive empirical study was conducted across 82 fine-grained categories, investigating three paradigms: fine-tuned encoder models, hierarchical classification, and ensemble methods. Leveraging a dataset of 27k Arabic medical question-answer pairs, an extensive ablation studies was conducted, comparing MARBERTv2, CAMeLBERT, two-stage hierarchical classifiers, and RAG-based approaches. The findings reveal that fine-tuned MARBERTv2 with data cleaning yields the best performance, achieving a macro F1-score of 0.3659 on the blind test set. In contrast, hierarchical methods surprisingly underperformed (0.332 F1) due to error propagation. The system ranked 26th on the official leaderboard."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="emad-eldin-2026-tashkees">
<titleInfo>
<title>Tashkees-AI at AbjadMed 2026: Flat vs. Hierarchical Classification for Fine-Grained Arabic Medical QA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatimah</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Emad Eldin</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 Tashkees-AI, a system developed for the AbjadMed 2026 Shared Task on Arabic Medical Question Classification. A comprehensive empirical study was conducted across 82 fine-grained categories, investigating three paradigms: fine-tuned encoder models, hierarchical classification, and ensemble methods. Leveraging a dataset of 27k Arabic medical question-answer pairs, an extensive ablation studies was conducted, comparing MARBERTv2, CAMeLBERT, two-stage hierarchical classifiers, and RAG-based approaches. The findings reveal that fine-tuned MARBERTv2 with data cleaning yields the best performance, achieving a macro F1-score of 0.3659 on the blind test set. In contrast, hierarchical methods surprisingly underperformed (0.332 F1) due to error propagation. The system ranked 26th on the official leaderboard.</abstract>
<identifier type="citekey">emad-eldin-2026-tashkees</identifier>
<location>
<url>https://aclanthology.org/2026.abjadnlp-1.20/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>137</start>
<end>143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tashkees-AI at AbjadMed 2026: Flat vs. Hierarchical Classification for Fine-Grained Arabic Medical QA
%A Emad Eldin, Fatimah Mohamed
%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 emad-eldin-2026-tashkees
%X This paper describes Tashkees-AI, a system developed for the AbjadMed 2026 Shared Task on Arabic Medical Question Classification. A comprehensive empirical study was conducted across 82 fine-grained categories, investigating three paradigms: fine-tuned encoder models, hierarchical classification, and ensemble methods. Leveraging a dataset of 27k Arabic medical question-answer pairs, an extensive ablation studies was conducted, comparing MARBERTv2, CAMeLBERT, two-stage hierarchical classifiers, and RAG-based approaches. The findings reveal that fine-tuned MARBERTv2 with data cleaning yields the best performance, achieving a macro F1-score of 0.3659 on the blind test set. In contrast, hierarchical methods surprisingly underperformed (0.332 F1) due to error propagation. The system ranked 26th on the official leaderboard.
%U https://aclanthology.org/2026.abjadnlp-1.20/
%P 137-143
Markdown (Informal)
[Tashkees-AI at AbjadMed 2026: Flat vs. Hierarchical Classification for Fine-Grained Arabic Medical QA](https://aclanthology.org/2026.abjadnlp-1.20/) (Emad Eldin, AbjadNLP 2026)
ACL