@inproceedings{osrf-etal-2026-burhan,
title = "{BURHAN} at Daleel Shared Task Subtask-1: A Multi-Label Transformer Pipeline for {A}rabic Argumentative Discourse Unit Classification",
author = "Osrf, Ahmed and
Baid, Eid Abo and
Abudalfa, Shadi",
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.170/",
pages = "1370--1374",
ISBN = "979-8-89176-497-2",
abstract = "This paper presents our system for Task 1 of the Daleel 2026 shared task, which assigns multiple discourse-function labels to Arabic paragraphs from editorials and debate transcripts. We fine-tune a monolingual Arabic encoder (MARBERTv2) with a label-weighted focal loss, multilabel-stratified k-fold crossvalidation, out-of-fold per-label threshold calibration, k-fold ensembling, and a genreconditioning prefix, in a two-stage protocol that first trains on the training split alone and then retrains on training+development. Internal cross-validation macro-F1 rises from 0.667 to 0.680 across the two stages. On the official test set, the system attains micro-F1 = 0.766 and macroF1 = 0.560, with markedly stronger micro-F1 on debate paragraphs (0.825) than editorials (0.633), and a smaller but consistent macro-F1 gap (0.554 vs. 0.456). Assumption is classified most reliably (F1 = 0.88{--}0.94) and Common Ground least reliably (F1 {\ensuremath{\leq}} 0.12), mirroring the low inter-annotator agreement reported for the same category in the source English scheme. We find a {\ensuremath{\sim}}0.12 gap between internal cross-validation and official test macro-F1, concentrated in low-support, genre-sensitive categories. Our code is publicly available at https://github.com/EidAhmed1/daleel2026{\_}task1{\_}project."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="osrf-etal-2026-burhan">
<titleInfo>
<title>BURHAN at Daleel Shared Task Subtask-1: A Multi-Label Transformer Pipeline for Arabic Argumentative Discourse Unit Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Osrf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eid</namePart>
<namePart type="given">Abo</namePart>
<namePart type="family">Baid</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>
<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 our system for Task 1 of the Daleel 2026 shared task, which assigns multiple discourse-function labels to Arabic paragraphs from editorials and debate transcripts. We fine-tune a monolingual Arabic encoder (MARBERTv2) with a label-weighted focal loss, multilabel-stratified k-fold crossvalidation, out-of-fold per-label threshold calibration, k-fold ensembling, and a genreconditioning prefix, in a two-stage protocol that first trains on the training split alone and then retrains on training+development. Internal cross-validation macro-F1 rises from 0.667 to 0.680 across the two stages. On the official test set, the system attains micro-F1 = 0.766 and macroF1 = 0.560, with markedly stronger micro-F1 on debate paragraphs (0.825) than editorials (0.633), and a smaller but consistent macro-F1 gap (0.554 vs. 0.456). Assumption is classified most reliably (F1 = 0.88–0.94) and Common Ground least reliably (F1 \ensuremathłeq 0.12), mirroring the low inter-annotator agreement reported for the same category in the source English scheme. We find a \ensuremath\sim0.12 gap between internal cross-validation and official test macro-F1, concentrated in low-support, genre-sensitive categories. Our code is publicly available at https://github.com/EidAhmed1/daleel2026_task1_project.</abstract>
<identifier type="citekey">osrf-etal-2026-burhan</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.170/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1370</start>
<end>1374</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BURHAN at Daleel Shared Task Subtask-1: A Multi-Label Transformer Pipeline for Arabic Argumentative Discourse Unit Classification
%A Osrf, Ahmed
%A Baid, Eid Abo
%A Abudalfa, Shadi
%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 osrf-etal-2026-burhan
%X This paper presents our system for Task 1 of the Daleel 2026 shared task, which assigns multiple discourse-function labels to Arabic paragraphs from editorials and debate transcripts. We fine-tune a monolingual Arabic encoder (MARBERTv2) with a label-weighted focal loss, multilabel-stratified k-fold crossvalidation, out-of-fold per-label threshold calibration, k-fold ensembling, and a genreconditioning prefix, in a two-stage protocol that first trains on the training split alone and then retrains on training+development. Internal cross-validation macro-F1 rises from 0.667 to 0.680 across the two stages. On the official test set, the system attains micro-F1 = 0.766 and macroF1 = 0.560, with markedly stronger micro-F1 on debate paragraphs (0.825) than editorials (0.633), and a smaller but consistent macro-F1 gap (0.554 vs. 0.456). Assumption is classified most reliably (F1 = 0.88–0.94) and Common Ground least reliably (F1 \ensuremathłeq 0.12), mirroring the low inter-annotator agreement reported for the same category in the source English scheme. We find a \ensuremath\sim0.12 gap between internal cross-validation and official test macro-F1, concentrated in low-support, genre-sensitive categories. Our code is publicly available at https://github.com/EidAhmed1/daleel2026_task1_project.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.170/
%P 1370-1374
Markdown (Informal)
[BURHAN at Daleel Shared Task Subtask-1: A Multi-Label Transformer Pipeline for Arabic Argumentative Discourse Unit Classification](https://aclanthology.org/2026.arabicnlp-sharedtasks.170/) (Osrf et al., ArabicNLP 2026)
ACL