@inproceedings{almasri-etal-2026-wathiq,
title = "Wathiq-{SPU} at {A}ra{S}eg Shared Task 2026: Calibrated Transformer Ensembles for {A}rabic Sentence Segmentation across Punctuation and Paragraph Conditions",
author = "Almasri, Salam and
Bostaty, Najat and
Al Shaabani, Bushra and
Alhossny, Raghad and
Sonbol, Riad",
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.120/",
pages = "971--976",
ISBN = "979-8-89176-497-2",
abstract = "Arabic sentence segmentation becomes substantially more difficult when punctuation and paragraph boundaries are unavailable. The AraSeg Shared Task 2026 provides a controlled benchmark for studying this problem under four conditions that progressively remove structural information. We present the Wathiq-SPU submission to all four closed-track conditions: Paragraph-Aware (PA), No-Punctuation Paragraph-Aware (NoPnx-PA), No-Paragraph (NP), and No-Punctuation No-Paragraph (NoPnx-NP). We formulate sentence segmentation as token-level binary boundary classification using pretrained Arabic Transformer encoders and combine calibrated predictions with track-specific ensemble strategies that adapt to the amount of available structural information. CAMeLBERT-MSA serves as our primary encoder, while the most challenging NoPnx-NP condition additionally benefits from AraELECTRA-based backbone diversity. Our experiments reveal that the most effective source of model diversity depends on task difficulty: diversity among independently trained models provides robust gains when some structural information is available, whereas backbone diversity becomes increasingly important when both punctuation and paragraph cues are removed. The selected systems achieve F1 scores of 93.4, 87.9, 90.0, and 84.8 on the PA, NoPnx-PA, NP, and NoPnx-NP tracks, respectively"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almasri-etal-2026-wathiq">
<titleInfo>
<title>Wathiq-SPU at AraSeg Shared Task 2026: Calibrated Transformer Ensembles for Arabic Sentence Segmentation across Punctuation and Paragraph Conditions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Almasri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Najat</namePart>
<namePart type="family">Bostaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bushra</namePart>
<namePart type="family">Al Shaabani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghad</namePart>
<namePart type="family">Alhossny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riad</namePart>
<namePart type="family">Sonbol</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 becomes substantially more difficult when punctuation and paragraph boundaries are unavailable. The AraSeg Shared Task 2026 provides a controlled benchmark for studying this problem under four conditions that progressively remove structural information. We present the Wathiq-SPU submission to all four closed-track conditions: Paragraph-Aware (PA), No-Punctuation Paragraph-Aware (NoPnx-PA), No-Paragraph (NP), and No-Punctuation No-Paragraph (NoPnx-NP). We formulate sentence segmentation as token-level binary boundary classification using pretrained Arabic Transformer encoders and combine calibrated predictions with track-specific ensemble strategies that adapt to the amount of available structural information. CAMeLBERT-MSA serves as our primary encoder, while the most challenging NoPnx-NP condition additionally benefits from AraELECTRA-based backbone diversity. Our experiments reveal that the most effective source of model diversity depends on task difficulty: diversity among independently trained models provides robust gains when some structural information is available, whereas backbone diversity becomes increasingly important when both punctuation and paragraph cues are removed. The selected systems achieve F1 scores of 93.4, 87.9, 90.0, and 84.8 on the PA, NoPnx-PA, NP, and NoPnx-NP tracks, respectively</abstract>
<identifier type="citekey">almasri-etal-2026-wathiq</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.120/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>971</start>
<end>976</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wathiq-SPU at AraSeg Shared Task 2026: Calibrated Transformer Ensembles for Arabic Sentence Segmentation across Punctuation and Paragraph Conditions
%A Almasri, Salam
%A Bostaty, Najat
%A Al Shaabani, Bushra
%A Alhossny, Raghad
%A Sonbol, Riad
%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 almasri-etal-2026-wathiq
%X Arabic sentence segmentation becomes substantially more difficult when punctuation and paragraph boundaries are unavailable. The AraSeg Shared Task 2026 provides a controlled benchmark for studying this problem under four conditions that progressively remove structural information. We present the Wathiq-SPU submission to all four closed-track conditions: Paragraph-Aware (PA), No-Punctuation Paragraph-Aware (NoPnx-PA), No-Paragraph (NP), and No-Punctuation No-Paragraph (NoPnx-NP). We formulate sentence segmentation as token-level binary boundary classification using pretrained Arabic Transformer encoders and combine calibrated predictions with track-specific ensemble strategies that adapt to the amount of available structural information. CAMeLBERT-MSA serves as our primary encoder, while the most challenging NoPnx-NP condition additionally benefits from AraELECTRA-based backbone diversity. Our experiments reveal that the most effective source of model diversity depends on task difficulty: diversity among independently trained models provides robust gains when some structural information is available, whereas backbone diversity becomes increasingly important when both punctuation and paragraph cues are removed. The selected systems achieve F1 scores of 93.4, 87.9, 90.0, and 84.8 on the PA, NoPnx-PA, NP, and NoPnx-NP tracks, respectively
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.120/
%P 971-976
Markdown (Informal)
[Wathiq-SPU at AraSeg Shared Task 2026: Calibrated Transformer Ensembles for Arabic Sentence Segmentation across Punctuation and Paragraph Conditions](https://aclanthology.org/2026.arabicnlp-sharedtasks.120/) (Almasri et al., ArabicNLP 2026)
ACL