@inproceedings{alsudairi-etal-2026-abjad,
title = "Abjad {AI} at {A}ra{S}eg Shared Task 2026: Auxiliary Loss for {A}rabic Sentence Segmentation",
author = "Alsudairi, Mohammed and
Alharthi, Naif and
Nono, Taif and
Alasmary, Faris and
Salamah, Anas Adel and
Sadah, Shouq and
Ghouti, Lahouari",
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.123/",
pages = "1004--1009",
ISBN = "979-8-89176-497-2",
abstract = "This paper describes the Abjad AI team{'}s sub- mission to the AraSeg 2026 Shared Task on Arabic sentence segmentation, covering the two punctuated tracks: Paragraph-Aware (PA) and No-Paragraph (NP). Rather than substituting a larger encoder, we retain the CAMeLBERT- MSA reference system and ask how much head- room remains in the task{'}s formulation. Our system combines four components: boundary labels aligned to each word{'}s final sub-token, an auxiliary classification head on the penul- timate encoder layer trained jointly with the final-layer head, class-weighted cross-entropy for boundary sparsity, and overlap-averaged decoding that scores documents of arbitrary length without truncation. We ablate each com- ponent in isolation, including the two that the reference system already uses. Our solution achieves F1 scores of 91.7 and 89.7 in the blind tests of the PA and NP sub-tasks, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alsudairi-etal-2026-abjad">
<titleInfo>
<title>Abjad AI at AraSeg Shared Task 2026: Auxiliary Loss for Arabic Sentence Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Alsudairi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naif</namePart>
<namePart type="family">Alharthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taif</namePart>
<namePart type="family">Nono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faris</namePart>
<namePart type="family">Alasmary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anas</namePart>
<namePart type="given">Adel</namePart>
<namePart type="family">Salamah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shouq</namePart>
<namePart type="family">Sadah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lahouari</namePart>
<namePart type="family">Ghouti</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>This paper describes the Abjad AI team’s sub- mission to the AraSeg 2026 Shared Task on Arabic sentence segmentation, covering the two punctuated tracks: Paragraph-Aware (PA) and No-Paragraph (NP). Rather than substituting a larger encoder, we retain the CAMeLBERT- MSA reference system and ask how much head- room remains in the task’s formulation. Our system combines four components: boundary labels aligned to each word’s final sub-token, an auxiliary classification head on the penul- timate encoder layer trained jointly with the final-layer head, class-weighted cross-entropy for boundary sparsity, and overlap-averaged decoding that scores documents of arbitrary length without truncation. We ablate each com- ponent in isolation, including the two that the reference system already uses. Our solution achieves F1 scores of 91.7 and 89.7 in the blind tests of the PA and NP sub-tasks, respectively.</abstract>
<identifier type="citekey">alsudairi-etal-2026-abjad</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.123/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1004</start>
<end>1009</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T Abjad AI at AraSeg Shared Task 2026: Auxiliary Loss for Arabic Sentence Segmentation %A Alsudairi, Mohammed %A Alharthi, Naif %A Nono, Taif %A Alasmary, Faris %A Salamah, Anas Adel %A Sadah, Shouq %A Ghouti, Lahouari %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 alsudairi-etal-2026-abjad %X This paper describes the Abjad AI team’s sub- mission to the AraSeg 2026 Shared Task on Arabic sentence segmentation, covering the two punctuated tracks: Paragraph-Aware (PA) and No-Paragraph (NP). Rather than substituting a larger encoder, we retain the CAMeLBERT- MSA reference system and ask how much head- room remains in the task’s formulation. Our system combines four components: boundary labels aligned to each word’s final sub-token, an auxiliary classification head on the penul- timate encoder layer trained jointly with the final-layer head, class-weighted cross-entropy for boundary sparsity, and overlap-averaged decoding that scores documents of arbitrary length without truncation. We ablate each com- ponent in isolation, including the two that the reference system already uses. Our solution achieves F1 scores of 91.7 and 89.7 in the blind tests of the PA and NP sub-tasks, respectively. %U https://aclanthology.org/2026.arabicnlp-sharedtasks.123/ %P 1004-1009
Markdown (Informal)
[Abjad AI at AraSeg Shared Task 2026: Auxiliary Loss for Arabic Sentence Segmentation](https://aclanthology.org/2026.arabicnlp-sharedtasks.123/) (Alsudairi et al., ArabicNLP 2026)