@inproceedings{sabry-ragab-2026-auc,
title = "{AUC} {DL} Lab at {A}ra{S}eg Shared Task 2026: Syntax-Aware Graphs, Bidirectionalized Decoders, and Encoders for {A}rabic Sentence Segmentation",
author = "Sabry, Mohamed and
Ragab, Yehia",
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.119/",
pages = "961--970",
ISBN = "979-8-89176-497-2",
abstract = "The AUC DL Lab system addresses the AraSeg 2026 shared task on Arabic sentence segmentation across four conditions: paragraph-aware (PA), no-paragraph (NP), no-punctuation paragraph-aware (NOPNX-PA), and no-punctuation no-paragraph (NOPNXNP), in both the closed and open tracks. We cast segmentation as imbalanced word-level boundary classification and pair fine-tuned Arabic encoders with two complementary architectures: HDP-GRAPH, which models syntactic structure via dependency-graph message passing, and a quantized decoder-only LLM using Just Pass Twice (JPT) with QLoRA for contextual boundary classification. Predictions are calibrated and combined through differential-evolution ensemble weighting. On the blind test set, our closed track systems reach 94.5, 90.8, 89.2, and 86.0 F1 (ranking 5th, 6th, 6th, 7th), and our open-track systems reach 94.6, 90.9, 89.7, and 86.0 F1 (ranking 3rd, 4th, 4th, 5th) on PA, NP, NOPNX-PA, and NOPNX-NP, respectively. Architectural diversity grows more valuable as punctuation and paragraph cues are removed, while external data yields only marginal gains once in-domain coverage is adequate."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sabry-ragab-2026-auc">
<titleInfo>
<title>AUC DL Lab at AraSeg Shared Task 2026: Syntax-Aware Graphs, Bidirectionalized Decoders, and Encoders for Arabic Sentence Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Sabry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yehia</namePart>
<namePart type="family">Ragab</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>The AUC DL Lab system addresses the AraSeg 2026 shared task on Arabic sentence segmentation across four conditions: paragraph-aware (PA), no-paragraph (NP), no-punctuation paragraph-aware (NOPNX-PA), and no-punctuation no-paragraph (NOPNXNP), in both the closed and open tracks. We cast segmentation as imbalanced word-level boundary classification and pair fine-tuned Arabic encoders with two complementary architectures: HDP-GRAPH, which models syntactic structure via dependency-graph message passing, and a quantized decoder-only LLM using Just Pass Twice (JPT) with QLoRA for contextual boundary classification. Predictions are calibrated and combined through differential-evolution ensemble weighting. On the blind test set, our closed track systems reach 94.5, 90.8, 89.2, and 86.0 F1 (ranking 5th, 6th, 6th, 7th), and our open-track systems reach 94.6, 90.9, 89.7, and 86.0 F1 (ranking 3rd, 4th, 4th, 5th) on PA, NP, NOPNX-PA, and NOPNX-NP, respectively. Architectural diversity grows more valuable as punctuation and paragraph cues are removed, while external data yields only marginal gains once in-domain coverage is adequate.</abstract>
<identifier type="citekey">sabry-ragab-2026-auc</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.119/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>961</start>
<end>970</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AUC DL Lab at AraSeg Shared Task 2026: Syntax-Aware Graphs, Bidirectionalized Decoders, and Encoders for Arabic Sentence Segmentation
%A Sabry, Mohamed
%A Ragab, Yehia
%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 sabry-ragab-2026-auc
%X The AUC DL Lab system addresses the AraSeg 2026 shared task on Arabic sentence segmentation across four conditions: paragraph-aware (PA), no-paragraph (NP), no-punctuation paragraph-aware (NOPNX-PA), and no-punctuation no-paragraph (NOPNXNP), in both the closed and open tracks. We cast segmentation as imbalanced word-level boundary classification and pair fine-tuned Arabic encoders with two complementary architectures: HDP-GRAPH, which models syntactic structure via dependency-graph message passing, and a quantized decoder-only LLM using Just Pass Twice (JPT) with QLoRA for contextual boundary classification. Predictions are calibrated and combined through differential-evolution ensemble weighting. On the blind test set, our closed track systems reach 94.5, 90.8, 89.2, and 86.0 F1 (ranking 5th, 6th, 6th, 7th), and our open-track systems reach 94.6, 90.9, 89.7, and 86.0 F1 (ranking 3rd, 4th, 4th, 5th) on PA, NP, NOPNX-PA, and NOPNX-NP, respectively. Architectural diversity grows more valuable as punctuation and paragraph cues are removed, while external data yields only marginal gains once in-domain coverage is adequate.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.119/
%P 961-970
Markdown (Informal)
[AUC DL Lab at AraSeg Shared Task 2026: Syntax-Aware Graphs, Bidirectionalized Decoders, and Encoders for Arabic Sentence Segmentation](https://aclanthology.org/2026.arabicnlp-sharedtasks.119/) (Sabry & Ragab, ArabicNLP 2026)
ACL