@inproceedings{abdelaziz-etal-2026-nu,
title = "{NU}{\_}{A}nalytics at Daleel 2026: Independent Label Scoring and Structured Span Prediction for {A}rabic Argumentative Discourse Mining",
author = "Abdelaziz, Abdelrahman Ahmad Saeed and
Emad, Hend and
Mohamed, Ensaf H.",
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.169/",
pages = "1358--1369",
ISBN = "979-8-89176-497-2",
abstract = "We present our closed-track systems for both subtasks of Daleel 2026, which targets Arabic argumentative discourse unit (ADU) mining over editorials and competitive debates. Task 1 is an imbalanced multi label paragraph classification problem, and Task 2 requires character-level detection and classification of ADU spans. For Task 1 we investigate two parameter-efficient decoder-LLM formulations: joint label generation with Qwen3.5-9B and independent label scoring with ALLaM-7B. The latter decomposes each paragraph into six explicit Yes/No decisions, giving every label direct supervision and a separate decision score; it achieves 0.6714 Macro-F1 on the evaluation phase and ranked 4th, while ablations show that additional class-balanced weighting degrades performance. For Task 2 we combine task-adaptive pretraining, Beginning-Inside-Outside Conditional Random Field (BIO-CRF) sequence labeling, boundary-jitter augmentation, character-space ensembling, and span post-processing over AraBERT-large, achieving an official F1 of 0.7523 (0.7931 on debates, 0.6417 on editorials) and ranking second. Across both tasks, our results support explicit label-wise supervision and span-level ensemble decisions as effective ways to handle label imbalance and boundary noise without aggressive reweighting, while short spans, rare classes, and genre variation remain challenging."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdelaziz-etal-2026-nu">
<titleInfo>
<title>NU_Analytics at Daleel 2026: Independent Label Scoring and Structured Span Prediction for Arabic Argumentative Discourse Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="given">Ahmad</namePart>
<namePart type="given">Saeed</namePart>
<namePart type="family">Abdelaziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Emad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ensaf</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Mohamed</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 present our closed-track systems for both subtasks of Daleel 2026, which targets Arabic argumentative discourse unit (ADU) mining over editorials and competitive debates. Task 1 is an imbalanced multi label paragraph classification problem, and Task 2 requires character-level detection and classification of ADU spans. For Task 1 we investigate two parameter-efficient decoder-LLM formulations: joint label generation with Qwen3.5-9B and independent label scoring with ALLaM-7B. The latter decomposes each paragraph into six explicit Yes/No decisions, giving every label direct supervision and a separate decision score; it achieves 0.6714 Macro-F1 on the evaluation phase and ranked 4th, while ablations show that additional class-balanced weighting degrades performance. For Task 2 we combine task-adaptive pretraining, Beginning-Inside-Outside Conditional Random Field (BIO-CRF) sequence labeling, boundary-jitter augmentation, character-space ensembling, and span post-processing over AraBERT-large, achieving an official F1 of 0.7523 (0.7931 on debates, 0.6417 on editorials) and ranking second. Across both tasks, our results support explicit label-wise supervision and span-level ensemble decisions as effective ways to handle label imbalance and boundary noise without aggressive reweighting, while short spans, rare classes, and genre variation remain challenging.</abstract>
<identifier type="citekey">abdelaziz-etal-2026-nu</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.169/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1358</start>
<end>1369</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NU_Analytics at Daleel 2026: Independent Label Scoring and Structured Span Prediction for Arabic Argumentative Discourse Mining
%A Abdelaziz, Abdelrahman Ahmad Saeed
%A Emad, Hend
%A Mohamed, Ensaf H.
%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 abdelaziz-etal-2026-nu
%X We present our closed-track systems for both subtasks of Daleel 2026, which targets Arabic argumentative discourse unit (ADU) mining over editorials and competitive debates. Task 1 is an imbalanced multi label paragraph classification problem, and Task 2 requires character-level detection and classification of ADU spans. For Task 1 we investigate two parameter-efficient decoder-LLM formulations: joint label generation with Qwen3.5-9B and independent label scoring with ALLaM-7B. The latter decomposes each paragraph into six explicit Yes/No decisions, giving every label direct supervision and a separate decision score; it achieves 0.6714 Macro-F1 on the evaluation phase and ranked 4th, while ablations show that additional class-balanced weighting degrades performance. For Task 2 we combine task-adaptive pretraining, Beginning-Inside-Outside Conditional Random Field (BIO-CRF) sequence labeling, boundary-jitter augmentation, character-space ensembling, and span post-processing over AraBERT-large, achieving an official F1 of 0.7523 (0.7931 on debates, 0.6417 on editorials) and ranking second. Across both tasks, our results support explicit label-wise supervision and span-level ensemble decisions as effective ways to handle label imbalance and boundary noise without aggressive reweighting, while short spans, rare classes, and genre variation remain challenging.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.169/
%P 1358-1369
Markdown (Informal)
[NU_Analytics at Daleel 2026: Independent Label Scoring and Structured Span Prediction for Arabic Argumentative Discourse Mining](https://aclanthology.org/2026.arabicnlp-sharedtasks.169/) (Abdelaziz et al., ArabicNLP 2026)
ACL