@inproceedings{nabhani-etal-2026-daleel,
title = "Daleel 2026 Shared Task on {A}rabic Argumentative Discourse Mining",
author = "Nabhani, Sara and
Bassyouni, Nahla and
Al-Zawqari, Ali and
Khader, Mohammad and
Khatib, Khalid Al",
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.161/",
pages = "1287--1298",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents Daleel 2026, the first shared task on argument mining in Arabic news editorials and competitive debates. Daleel includes two tasks: Task 1 identifies which of six argumentative discourse unit (ADU) categories are present in a paragraph, while Task 2 locates the units with their labels and exact text spans. The tasks are performed using a new corpus of 30 documents, 1,042 paragraphs, and about 76k words. Twenty-nine teams registered, 12 participated, and 10 submitted system papers. Both tasks have Closed and Open tracks. The best results for the Closed track were 0.7117 macro-F1 in Task 1 and 0.7547 modified overlap F1 in Task 2. The results show different insights: the best Closed-track score of each team was higher on debates than on editorials. A broad range of approaches was used in Task 1 submissions, including Arabic encoders, large language models, rules, and ensembles. Task 2 systems, in particular the top-ranked ones, were more similar and mainly used CRF or Viterbi decoding with combinations of models or training runs. The rare ADU categories remained difficult in both tasks, and identifying exact span boundaries was an additional challenge in Task 2."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nabhani-etal-2026-daleel">
<titleInfo>
<title>Daleel 2026 Shared Task on Arabic Argumentative Discourse Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Nabhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nahla</namePart>
<namePart type="family">Bassyouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Al-Zawqari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Khader</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="given">Al</namePart>
<namePart type="family">Khatib</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>This paper presents Daleel 2026, the first shared task on argument mining in Arabic news editorials and competitive debates. Daleel includes two tasks: Task 1 identifies which of six argumentative discourse unit (ADU) categories are present in a paragraph, while Task 2 locates the units with their labels and exact text spans. The tasks are performed using a new corpus of 30 documents, 1,042 paragraphs, and about 76k words. Twenty-nine teams registered, 12 participated, and 10 submitted system papers. Both tasks have Closed and Open tracks. The best results for the Closed track were 0.7117 macro-F1 in Task 1 and 0.7547 modified overlap F1 in Task 2. The results show different insights: the best Closed-track score of each team was higher on debates than on editorials. A broad range of approaches was used in Task 1 submissions, including Arabic encoders, large language models, rules, and ensembles. Task 2 systems, in particular the top-ranked ones, were more similar and mainly used CRF or Viterbi decoding with combinations of models or training runs. The rare ADU categories remained difficult in both tasks, and identifying exact span boundaries was an additional challenge in Task 2.</abstract>
<identifier type="citekey">nabhani-etal-2026-daleel</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.161/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1287</start>
<end>1298</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Daleel 2026 Shared Task on Arabic Argumentative Discourse Mining
%A Nabhani, Sara
%A Bassyouni, Nahla
%A Al-Zawqari, Ali
%A Khader, Mohammad
%A Khatib, Khalid Al
%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 nabhani-etal-2026-daleel
%X This paper presents Daleel 2026, the first shared task on argument mining in Arabic news editorials and competitive debates. Daleel includes two tasks: Task 1 identifies which of six argumentative discourse unit (ADU) categories are present in a paragraph, while Task 2 locates the units with their labels and exact text spans. The tasks are performed using a new corpus of 30 documents, 1,042 paragraphs, and about 76k words. Twenty-nine teams registered, 12 participated, and 10 submitted system papers. Both tasks have Closed and Open tracks. The best results for the Closed track were 0.7117 macro-F1 in Task 1 and 0.7547 modified overlap F1 in Task 2. The results show different insights: the best Closed-track score of each team was higher on debates than on editorials. A broad range of approaches was used in Task 1 submissions, including Arabic encoders, large language models, rules, and ensembles. Task 2 systems, in particular the top-ranked ones, were more similar and mainly used CRF or Viterbi decoding with combinations of models or training runs. The rare ADU categories remained difficult in both tasks, and identifying exact span boundaries was an additional challenge in Task 2.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.161/
%P 1287-1298
Markdown (Informal)
[Daleel 2026 Shared Task on Arabic Argumentative Discourse Mining](https://aclanthology.org/2026.arabicnlp-sharedtasks.161/) (Nabhani et al., ArabicNLP 2026)
ACL
- Sara Nabhani, Nahla Bassyouni, Ali Al-Zawqari, Mohammad Khader, and Khalid Al Khatib. 2026. Daleel 2026 Shared Task on Arabic Argumentative Discourse Mining. In Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks, pages 1287–1298, Budapest, Hungary. Association for Computational Linguistics.