@inproceedings{el-haj-etal-2026-aragenre,
title = "{A}ra{G}enre 2026: A Hierarchical Definition-Guided {A}rabic Genre Classification Shared Task",
author = "El-Haj, Mo and
Ezzini, Saad and
Abudalfa, Shadi and
Jarrar, Mustafa and
Chi, Nguyen Minh and
Nguyen, Quan Minh",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.27/",
pages = "231--245",
ISBN = "979-8-89176-497-2",
abstract = "AraGenre 2026 is a shared task on hierarchical, definition-guided Arabic genre classification under limited supervision and substantial distribution shift. Systems assign each text a broad label and a specific label using an inventory of six broad branches and 74 defined final genres. The final benchmark contains 27,972 source-derived Arabic segments, spanning Modern Standard Arabic, Classical Arabic, and dialectal material, while the released labelled examples are small and primarily synthetic. Final specific classes are absent from the released labelled data, but their English names and definitions are provided. The task received 46 registrations and 373 submissions, with 17 ranked final entries and 11 system description papers. Thaka achieved the highest official Hierarchical Macro F1 at 73.52, followed by HP at 71.69 and NAMAA-1 at 70.13. Broad classification was consistently stronger than specific classification. The documented systems frequently combine label semantics with multilingual retrieval, LLM judging, pseudo-labelling, reranking, or calibration. We clarify the resource-driven taxonomy and inherited gold labels, distinguish combined distribution shift from isolated unseen-label effects, and provide systematic validation of the final evaluation data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-haj-etal-2026-aragenre">
<titleInfo>
<title>AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saad</namePart>
<namePart type="family">Ezzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shadi</namePart>
<namePart type="family">Abudalfa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Jarrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="given">Minh</namePart>
<namePart type="family">Chi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="given">Minh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>AraGenre 2026 is a shared task on hierarchical, definition-guided Arabic genre classification under limited supervision and substantial distribution shift. Systems assign each text a broad label and a specific label using an inventory of six broad branches and 74 defined final genres. The final benchmark contains 27,972 source-derived Arabic segments, spanning Modern Standard Arabic, Classical Arabic, and dialectal material, while the released labelled examples are small and primarily synthetic. Final specific classes are absent from the released labelled data, but their English names and definitions are provided. The task received 46 registrations and 373 submissions, with 17 ranked final entries and 11 system description papers. Thaka achieved the highest official Hierarchical Macro F1 at 73.52, followed by HP at 71.69 and NAMAA-1 at 70.13. Broad classification was consistently stronger than specific classification. The documented systems frequently combine label semantics with multilingual retrieval, LLM judging, pseudo-labelling, reranking, or calibration. We clarify the resource-driven taxonomy and inherited gold labels, distinguish combined distribution shift from isolated unseen-label effects, and provide systematic validation of the final evaluation data.</abstract>
<identifier type="citekey">el-haj-etal-2026-aragenre</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.27/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>231</start>
<end>245</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task
%A El-Haj, Mo
%A Ezzini, Saad
%A Abudalfa, Shadi
%A Jarrar, Mustafa
%A Chi, Nguyen Minh
%A Nguyen, Quan Minh
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F el-haj-etal-2026-aragenre
%X AraGenre 2026 is a shared task on hierarchical, definition-guided Arabic genre classification under limited supervision and substantial distribution shift. Systems assign each text a broad label and a specific label using an inventory of six broad branches and 74 defined final genres. The final benchmark contains 27,972 source-derived Arabic segments, spanning Modern Standard Arabic, Classical Arabic, and dialectal material, while the released labelled examples are small and primarily synthetic. Final specific classes are absent from the released labelled data, but their English names and definitions are provided. The task received 46 registrations and 373 submissions, with 17 ranked final entries and 11 system description papers. Thaka achieved the highest official Hierarchical Macro F1 at 73.52, followed by HP at 71.69 and NAMAA-1 at 70.13. Broad classification was consistently stronger than specific classification. The documented systems frequently combine label semantics with multilingual retrieval, LLM judging, pseudo-labelling, reranking, or calibration. We clarify the resource-driven taxonomy and inherited gold labels, distinguish combined distribution shift from isolated unseen-label effects, and provide systematic validation of the final evaluation data.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.27/
%P 231-245
Markdown (Informal)
[AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task](https://aclanthology.org/2026.arabicnlp-sharedtasks.27/) (El-Haj et al., ArabicNLP 2026)
ACL