@inproceedings{hossain-2026-axiom-araseg,
title = "Axiom at {A}ra{S}eg Shared Task 2026: A Regularized Dual-Model Ensemble with Domain-Adaptive Pretraining for {A}rabic Sentence Segmentation",
author = "Hossain, Md. Ajwad",
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.113/",
pages = "922--926",
ISBN = "979-8-89176-497-2",
abstract = "Identifying sentence boundaries in Arabic text is a challenging token classification task due to extreme dialectal variations, the absence of rigid punctuation rules, and document lengths that frequently exceed the capacity of standard transformer models. In this paper, we describe Team Axiom{'}s submission to the Paragraph-Aware Open track of the AraSeg Shared Task 2026. We propose a highly regularized, dual-model ensemble combining MARBERTv2 and CAMeLBERT-MSA. To address the challenge of excessively long documents, we employ a sliding-window tokenization strategy. Furthermore, we adapt our base models to the task corpus using Domain-Adaptive Pretraining (DAPT). Our final system achieved a Macro-F1 score of 90.2{\%} (Precision: 91.9{\%}, Recall: 89.5{\%}), securing 7th place in the shared task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hossain-2026-axiom-araseg">
<titleInfo>
<title>Axiom at AraSeg Shared Task 2026: A Regularized Dual-Model Ensemble with Domain-Adaptive Pretraining for Arabic Sentence Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Ajwad</namePart>
<namePart type="family">Hossain</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>Identifying sentence boundaries in Arabic text is a challenging token classification task due to extreme dialectal variations, the absence of rigid punctuation rules, and document lengths that frequently exceed the capacity of standard transformer models. In this paper, we describe Team Axiom’s submission to the Paragraph-Aware Open track of the AraSeg Shared Task 2026. We propose a highly regularized, dual-model ensemble combining MARBERTv2 and CAMeLBERT-MSA. To address the challenge of excessively long documents, we employ a sliding-window tokenization strategy. Furthermore, we adapt our base models to the task corpus using Domain-Adaptive Pretraining (DAPT). Our final system achieved a Macro-F1 score of 90.2% (Precision: 91.9%, Recall: 89.5%), securing 7th place in the shared task.</abstract>
<identifier type="citekey">hossain-2026-axiom-araseg</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.113/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>922</start>
<end>926</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Axiom at AraSeg Shared Task 2026: A Regularized Dual-Model Ensemble with Domain-Adaptive Pretraining for Arabic Sentence Segmentation
%A Hossain, Md. Ajwad
%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 hossain-2026-axiom-araseg
%X Identifying sentence boundaries in Arabic text is a challenging token classification task due to extreme dialectal variations, the absence of rigid punctuation rules, and document lengths that frequently exceed the capacity of standard transformer models. In this paper, we describe Team Axiom’s submission to the Paragraph-Aware Open track of the AraSeg Shared Task 2026. We propose a highly regularized, dual-model ensemble combining MARBERTv2 and CAMeLBERT-MSA. To address the challenge of excessively long documents, we employ a sliding-window tokenization strategy. Furthermore, we adapt our base models to the task corpus using Domain-Adaptive Pretraining (DAPT). Our final system achieved a Macro-F1 score of 90.2% (Precision: 91.9%, Recall: 89.5%), securing 7th place in the shared task.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.113/
%P 922-926
Markdown (Informal)
[Axiom at AraSeg Shared Task 2026: A Regularized Dual-Model Ensemble with Domain-Adaptive Pretraining for Arabic Sentence Segmentation](https://aclanthology.org/2026.arabicnlp-sharedtasks.113/) (Hossain, ArabicNLP 2026)
ACL