@inproceedings{usmani-2026-solodiscourse,
title = "Solodiscourse at Daleel 2026: Lexically-Augmented Focal-Loss Ensembling for {A}rabic Argumentative Discourse Unit Classification",
author = "Usmani, Turab Hussain",
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.171/",
pages = "1375--1379",
ISBN = "979-8-89176-497-2",
abstract = "We describe our submission to Task 1 (Argumentative Discourse Unit Classification) of the Daleel 2026 shared task on Arabic argument mining, in the closed track. Given a paragraph from an Arabic editorial or debate transcript, the task is to predict the multi-label set of argumentative functions it contains, drawn from six classes: common ground, assumption, testimony, statistics, anecdote, and other. Our system fine-tunes a pretrained Arabic encoder, comparing AraBERT, MARBERT, and CAMeLBERT-mix, augmented with a small side-channel of hand-crafted lexical features motivated directly by the task{'}s class definitions (e.g., reporting verbs for testimony, digit/percentage patterns for statistics), trained with a class-balanced focal loss and combined into a 5-fold cross-validation ensemble; CAMeLBERT-mix was selected as the final encoder for all submitted configurations. In the dev phase, our Both-domain configuration achieved an overall macro-F1 of 0.5600 (editorial 0.4350, debate 0.4900). On the official test-phase Codabench leaderboard, our Both-domain configuration achieved an overall macro-F1 of 0.5265 (editorial 0.3838, debate 0.4943), ranking 10th; our Editorial-only configuration reached an overall macro-F1 of 0.4544 (editorial 0.3249, debate 0.4509). We report two findings grounded in these results: overall (pooled) macro-F1 consistently exceeds the macro-F1 computed on either genre subset alone, and our editorial-only model unexpectedly scores higher macro-F1 on the out-of-domain debate subset than on its own in-domain editorial subset. We discuss both as likely artifacts of per-class support sparsity at the smaller genre-subset scale rather than genuine cross-domain superiority, though we did not conduct a formal ablation study or systematic error analysis to confirm this, which we flag as the primary limitation of this report. Our code is available at https://github.com/turab-usmani/daleel-task1-closedtrack."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="usmani-2026-solodiscourse">
<titleInfo>
<title>Solodiscourse at Daleel 2026: Lexically-Augmented Focal-Loss Ensembling for Arabic Argumentative Discourse Unit Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Turab</namePart>
<namePart type="given">Hussain</namePart>
<namePart type="family">Usmani</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>We describe our submission to Task 1 (Argumentative Discourse Unit Classification) of the Daleel 2026 shared task on Arabic argument mining, in the closed track. Given a paragraph from an Arabic editorial or debate transcript, the task is to predict the multi-label set of argumentative functions it contains, drawn from six classes: common ground, assumption, testimony, statistics, anecdote, and other. Our system fine-tunes a pretrained Arabic encoder, comparing AraBERT, MARBERT, and CAMeLBERT-mix, augmented with a small side-channel of hand-crafted lexical features motivated directly by the task’s class definitions (e.g., reporting verbs for testimony, digit/percentage patterns for statistics), trained with a class-balanced focal loss and combined into a 5-fold cross-validation ensemble; CAMeLBERT-mix was selected as the final encoder for all submitted configurations. In the dev phase, our Both-domain configuration achieved an overall macro-F1 of 0.5600 (editorial 0.4350, debate 0.4900). On the official test-phase Codabench leaderboard, our Both-domain configuration achieved an overall macro-F1 of 0.5265 (editorial 0.3838, debate 0.4943), ranking 10th; our Editorial-only configuration reached an overall macro-F1 of 0.4544 (editorial 0.3249, debate 0.4509). We report two findings grounded in these results: overall (pooled) macro-F1 consistently exceeds the macro-F1 computed on either genre subset alone, and our editorial-only model unexpectedly scores higher macro-F1 on the out-of-domain debate subset than on its own in-domain editorial subset. We discuss both as likely artifacts of per-class support sparsity at the smaller genre-subset scale rather than genuine cross-domain superiority, though we did not conduct a formal ablation study or systematic error analysis to confirm this, which we flag as the primary limitation of this report. Our code is available at https://github.com/turab-usmani/daleel-task1-closedtrack.</abstract>
<identifier type="citekey">usmani-2026-solodiscourse</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.171/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1375</start>
<end>1379</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Solodiscourse at Daleel 2026: Lexically-Augmented Focal-Loss Ensembling for Arabic Argumentative Discourse Unit Classification
%A Usmani, Turab Hussain
%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 usmani-2026-solodiscourse
%X We describe our submission to Task 1 (Argumentative Discourse Unit Classification) of the Daleel 2026 shared task on Arabic argument mining, in the closed track. Given a paragraph from an Arabic editorial or debate transcript, the task is to predict the multi-label set of argumentative functions it contains, drawn from six classes: common ground, assumption, testimony, statistics, anecdote, and other. Our system fine-tunes a pretrained Arabic encoder, comparing AraBERT, MARBERT, and CAMeLBERT-mix, augmented with a small side-channel of hand-crafted lexical features motivated directly by the task’s class definitions (e.g., reporting verbs for testimony, digit/percentage patterns for statistics), trained with a class-balanced focal loss and combined into a 5-fold cross-validation ensemble; CAMeLBERT-mix was selected as the final encoder for all submitted configurations. In the dev phase, our Both-domain configuration achieved an overall macro-F1 of 0.5600 (editorial 0.4350, debate 0.4900). On the official test-phase Codabench leaderboard, our Both-domain configuration achieved an overall macro-F1 of 0.5265 (editorial 0.3838, debate 0.4943), ranking 10th; our Editorial-only configuration reached an overall macro-F1 of 0.4544 (editorial 0.3249, debate 0.4509). We report two findings grounded in these results: overall (pooled) macro-F1 consistently exceeds the macro-F1 computed on either genre subset alone, and our editorial-only model unexpectedly scores higher macro-F1 on the out-of-domain debate subset than on its own in-domain editorial subset. We discuss both as likely artifacts of per-class support sparsity at the smaller genre-subset scale rather than genuine cross-domain superiority, though we did not conduct a formal ablation study or systematic error analysis to confirm this, which we flag as the primary limitation of this report. Our code is available at https://github.com/turab-usmani/daleel-task1-closedtrack.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.171/
%P 1375-1379
Markdown (Informal)
[Solodiscourse at Daleel 2026: Lexically-Augmented Focal-Loss Ensembling for Arabic Argumentative Discourse Unit Classification](https://aclanthology.org/2026.arabicnlp-sharedtasks.171/) (Usmani, ArabicNLP 2026)
ACL