@inproceedings{eid-etal-2026-dxmultihead,
title = "{D}x{M}ulti{H}ead at {A}ra{S}eg Shared Task 2026: Alignment-Safe Sequence Labeling and Weighted Ensembling for {A}rabic Sentence Segmentation",
author = "Eid, Muhammad Bahaa Alsayed and
Khaled, Mohamed and
Hany, Mena",
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.118/",
pages = "956--960",
ISBN = "979-8-89176-497-2",
abstract = "Sentence boundary detection in Arabic is inherently challenging due to ambiguous orthographic punctuation conventions, prolific coordinating conjunction clitics, and extensive stylistic variability across literary, religious, news, and web domains. In this paper, we present our system submission to the Closed Track of the AraSeg 2026 Shared Task. We formulate sentence boundary detection as a token-level sequence classification problem utilizing an ensemble of fine-tuned Arabic Transformer encoders: AraBERTv02, CAMeLBERT-MSA, and ARBERTv2. Our pipeline integrates an alignment-safe normalization strategy that strictly preserves gold token spans, overlapping sliding-window logit margin aggregation to counteract chunk-boundary degradation, stochastic punctuation masking during training, and calibrated positive-class loss weighting. In the official blind evaluation across eight diverse genres, our framework demonstrated strong boundary recovery across all four task tracks, securing 2nd place in both the Paragraph-Aware setting ($F_1 = 95.0\%$) and the No-Paragraph setting ($F_1 = 91.3\%$)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eid-etal-2026-dxmultihead">
<titleInfo>
<title>DxMultiHead at AraSeg Shared Task 2026: Alignment-Safe Sequence Labeling and Weighted Ensembling for Arabic Sentence Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Bahaa</namePart>
<namePart type="given">Alsayed</namePart>
<namePart type="family">Eid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Khaled</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mena</namePart>
<namePart type="family">Hany</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>Sentence boundary detection in Arabic is inherently challenging due to ambiguous orthographic punctuation conventions, prolific coordinating conjunction clitics, and extensive stylistic variability across literary, religious, news, and web domains. In this paper, we present our system submission to the Closed Track of the AraSeg 2026 Shared Task. We formulate sentence boundary detection as a token-level sequence classification problem utilizing an ensemble of fine-tuned Arabic Transformer encoders: AraBERTv02, CAMeLBERT-MSA, and ARBERTv2. Our pipeline integrates an alignment-safe normalization strategy that strictly preserves gold token spans, overlapping sliding-window logit margin aggregation to counteract chunk-boundary degradation, stochastic punctuation masking during training, and calibrated positive-class loss weighting. In the official blind evaluation across eight diverse genres, our framework demonstrated strong boundary recovery across all four task tracks, securing 2nd place in both the Paragraph-Aware setting (F₁ = 95.0%) and the No-Paragraph setting (F₁ = 91.3%).</abstract>
<identifier type="citekey">eid-etal-2026-dxmultihead</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.118/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>956</start>
<end>960</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DxMultiHead at AraSeg Shared Task 2026: Alignment-Safe Sequence Labeling and Weighted Ensembling for Arabic Sentence Segmentation
%A Eid, Muhammad Bahaa Alsayed
%A Khaled, Mohamed
%A Hany, Mena
%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 eid-etal-2026-dxmultihead
%X Sentence boundary detection in Arabic is inherently challenging due to ambiguous orthographic punctuation conventions, prolific coordinating conjunction clitics, and extensive stylistic variability across literary, religious, news, and web domains. In this paper, we present our system submission to the Closed Track of the AraSeg 2026 Shared Task. We formulate sentence boundary detection as a token-level sequence classification problem utilizing an ensemble of fine-tuned Arabic Transformer encoders: AraBERTv02, CAMeLBERT-MSA, and ARBERTv2. Our pipeline integrates an alignment-safe normalization strategy that strictly preserves gold token spans, overlapping sliding-window logit margin aggregation to counteract chunk-boundary degradation, stochastic punctuation masking during training, and calibrated positive-class loss weighting. In the official blind evaluation across eight diverse genres, our framework demonstrated strong boundary recovery across all four task tracks, securing 2nd place in both the Paragraph-Aware setting (F₁ = 95.0%) and the No-Paragraph setting (F₁ = 91.3%).
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.118/
%P 956-960
Markdown (Informal)
[DxMultiHead at AraSeg Shared Task 2026: Alignment-Safe Sequence Labeling and Weighted Ensembling for Arabic Sentence Segmentation](https://aclanthology.org/2026.arabicnlp-sharedtasks.118/) (Eid et al., ArabicNLP 2026)
ACL