@inproceedings{elaraby-2026-mostafaelaraby,
title = "{M}ostafa{E}l{A}raby at {A}rabic Segmentationtitle Shared Task 2026: Combining Lexical and Punctuation Evidence across Aligned Text View",
author = "ElAraby, Mostafa",
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.111/",
pages = "906--911",
ISBN = "979-8-89176-497-2",
abstract = "Arabic sentence segmentation without punctuation or paragraph breaks requires predicting boundaries from context. The AraSeg Open Track supplies a parallel punctuated view, but its marks do not consistently indicate sentence endings. We train two CAMeLBERT-MSA ensembles, one for the target No-Punctuation No-Paragraph view and one for the auxiliary No-Paragraph view. A discrete rule combines their boundary decisions with punctuation classes projected onto the target words. Model fitting and selection use only the 174-document official training split: five-fold cross-validation selects the training duration, and out-of-fold predictions calibrate the decoders and fusion rule. Development is reserved for evaluation, and the public test is unused. The system achieves 84.61 document-macro F1 on development and 84.88 on the official blind test, with blind precision of 81.87 and recall of 89.50. It predicts too many boundaries in 80.6{\%} of development documents, although some of its lowest scores result from missed boundaries."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elaraby-2026-mostafaelaraby">
<titleInfo>
<title>MostafaElAraby at Arabic Segmentationtitle Shared Task 2026: Combining Lexical and Punctuation Evidence across Aligned Text View</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mostafa</namePart>
<namePart type="family">ElAraby</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>Arabic sentence segmentation without punctuation or paragraph breaks requires predicting boundaries from context. The AraSeg Open Track supplies a parallel punctuated view, but its marks do not consistently indicate sentence endings. We train two CAMeLBERT-MSA ensembles, one for the target No-Punctuation No-Paragraph view and one for the auxiliary No-Paragraph view. A discrete rule combines their boundary decisions with punctuation classes projected onto the target words. Model fitting and selection use only the 174-document official training split: five-fold cross-validation selects the training duration, and out-of-fold predictions calibrate the decoders and fusion rule. Development is reserved for evaluation, and the public test is unused. The system achieves 84.61 document-macro F1 on development and 84.88 on the official blind test, with blind precision of 81.87 and recall of 89.50. It predicts too many boundaries in 80.6% of development documents, although some of its lowest scores result from missed boundaries.</abstract>
<identifier type="citekey">elaraby-2026-mostafaelaraby</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.111/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>906</start>
<end>911</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MostafaElAraby at Arabic Segmentationtitle Shared Task 2026: Combining Lexical and Punctuation Evidence across Aligned Text View
%A ElAraby, Mostafa
%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 elaraby-2026-mostafaelaraby
%X Arabic sentence segmentation without punctuation or paragraph breaks requires predicting boundaries from context. The AraSeg Open Track supplies a parallel punctuated view, but its marks do not consistently indicate sentence endings. We train two CAMeLBERT-MSA ensembles, one for the target No-Punctuation No-Paragraph view and one for the auxiliary No-Paragraph view. A discrete rule combines their boundary decisions with punctuation classes projected onto the target words. Model fitting and selection use only the 174-document official training split: five-fold cross-validation selects the training duration, and out-of-fold predictions calibrate the decoders and fusion rule. Development is reserved for evaluation, and the public test is unused. The system achieves 84.61 document-macro F1 on development and 84.88 on the official blind test, with blind precision of 81.87 and recall of 89.50. It predicts too many boundaries in 80.6% of development documents, although some of its lowest scores result from missed boundaries.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.111/
%P 906-911
Markdown (Informal)
[MostafaElAraby at Arabic Segmentationtitle Shared Task 2026: Combining Lexical and Punctuation Evidence across Aligned Text View](https://aclanthology.org/2026.arabicnlp-sharedtasks.111/) (ElAraby, ArabicNLP 2026)
ACL