@inproceedings{elkholy-etal-2026-arabic,
title = "{A}rabic Sentence Segmentation Shared Task 2026",
author = "Elkholy, Mohammed and
Elmadani, Khalid N. and
Habash, Nizar and
Alhafni, Bashar",
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.110/",
pages = "894--905",
ISBN = "979-8-89176-497-2",
abstract = "We present the findings of the Arabic Sentence Segmentation (AraSEG) Shared Task, organized at the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026). Given an Arabic document, the task requires systems to identify sentence boundaries and segment the text into coherent sentences. Systems are evaluated on the genre-diverse AraSEG corpus under four input settings that vary in punctuation availability and paragraph structure, each with a Closed Track restricted to the provided training data and an Open Track permitting publicly available external resources. 22 teams from 13 countries registered, 16 submitted systems, and 14 submitted system-description papers. Across the eight subtask-track combinations, the best systems achieve F1 scores ranging from 89.1 to 95.3. Performance declines as segmentation cues are removed, with the largest drop occurring when both punctuation and paragraph structure are unavailable. Pretrained-encoder ensembles and careful prediction calibration emerge as the most effective approaches, while gains from LLMs, external data, and complex architectures vary across systems and settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elkholy-etal-2026-arabic">
<titleInfo>
<title>Arabic Sentence Segmentation Shared Task 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Elkholy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Elmadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</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 the findings of the Arabic Sentence Segmentation (AraSEG) Shared Task, organized at the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026). Given an Arabic document, the task requires systems to identify sentence boundaries and segment the text into coherent sentences. Systems are evaluated on the genre-diverse AraSEG corpus under four input settings that vary in punctuation availability and paragraph structure, each with a Closed Track restricted to the provided training data and an Open Track permitting publicly available external resources. 22 teams from 13 countries registered, 16 submitted systems, and 14 submitted system-description papers. Across the eight subtask-track combinations, the best systems achieve F1 scores ranging from 89.1 to 95.3. Performance declines as segmentation cues are removed, with the largest drop occurring when both punctuation and paragraph structure are unavailable. Pretrained-encoder ensembles and careful prediction calibration emerge as the most effective approaches, while gains from LLMs, external data, and complex architectures vary across systems and settings.</abstract>
<identifier type="citekey">elkholy-etal-2026-arabic</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.110/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>894</start>
<end>905</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Sentence Segmentation Shared Task 2026
%A Elkholy, Mohammed
%A Elmadani, Khalid N.
%A Habash, Nizar
%A Alhafni, Bashar
%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 elkholy-etal-2026-arabic
%X We present the findings of the Arabic Sentence Segmentation (AraSEG) Shared Task, organized at the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026). Given an Arabic document, the task requires systems to identify sentence boundaries and segment the text into coherent sentences. Systems are evaluated on the genre-diverse AraSEG corpus under four input settings that vary in punctuation availability and paragraph structure, each with a Closed Track restricted to the provided training data and an Open Track permitting publicly available external resources. 22 teams from 13 countries registered, 16 submitted systems, and 14 submitted system-description papers. Across the eight subtask-track combinations, the best systems achieve F1 scores ranging from 89.1 to 95.3. Performance declines as segmentation cues are removed, with the largest drop occurring when both punctuation and paragraph structure are unavailable. Pretrained-encoder ensembles and careful prediction calibration emerge as the most effective approaches, while gains from LLMs, external data, and complex architectures vary across systems and settings.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.110/
%P 894-905
Markdown (Informal)
[Arabic Sentence Segmentation Shared Task 2026](https://aclanthology.org/2026.arabicnlp-sharedtasks.110/) (Elkholy et al., ArabicNLP 2026)
ACL
- Mohammed Elkholy, Khalid N. Elmadani, Nizar Habash, and Bashar Alhafni. 2026. Arabic Sentence Segmentation Shared Task 2026. In Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks, pages 894–905, Budapest, Hungary. Association for Computational Linguistics.