@inproceedings{elmasry-etal-2026-faamg,
title = "{FAAMG} at {A}ra{S}eg Shared Task 2026: Cross-Architecture Ensembling for Punctuation-Free {A}rabic Segmentation",
author = "Elmasry, Gaser and
Elbedewy, Abdulrahman and
Taha, Abdelrahman Wael Atef and
Seddik, Fahd and
Abdelmoniem, Mohamed Ahmed Mohamed",
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.121/",
pages = "977--994",
ISBN = "979-8-89176-497-2",
abstract = "Arabic sentence segmentation without punctuation or paragraph boundaries requires models to infer boundaries only from lexical, syntactic, and discourse context. We describe FAAMG{'}s submission in the closed track of AraSeg 2026 Subtask 4 (NoPnx-NP), restricted to only 174 training documents for fine-tuning. Our system is a weighted ensemble of eight models based on AraBERT, SaT, and CAMeLBERT BiLSTM-CRF. The ensemble covers a variety of regularization, encoder capacity, and sequence modeling. The resulting system achieves 86.7 document-macro F1 on the Blind Test set ranking fourth on the leaderboard. Through leave-one-out ablations we show that the ensemble contributes complementary information over the individual models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elmasry-etal-2026-faamg">
<titleInfo>
<title>FAAMG at AraSeg Shared Task 2026: Cross-Architecture Ensembling for Punctuation-Free Arabic Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaser</namePart>
<namePart type="family">Elmasry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">Elbedewy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="given">Wael</namePart>
<namePart type="given">Atef</namePart>
<namePart type="family">Taha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahd</namePart>
<namePart type="family">Seddik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Ahmed</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Abdelmoniem</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 without punctuation or paragraph boundaries requires models to infer boundaries only from lexical, syntactic, and discourse context. We describe FAAMG’s submission in the closed track of AraSeg 2026 Subtask 4 (NoPnx-NP), restricted to only 174 training documents for fine-tuning. Our system is a weighted ensemble of eight models based on AraBERT, SaT, and CAMeLBERT BiLSTM-CRF. The ensemble covers a variety of regularization, encoder capacity, and sequence modeling. The resulting system achieves 86.7 document-macro F1 on the Blind Test set ranking fourth on the leaderboard. Through leave-one-out ablations we show that the ensemble contributes complementary information over the individual models.</abstract>
<identifier type="citekey">elmasry-etal-2026-faamg</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.121/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>977</start>
<end>994</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FAAMG at AraSeg Shared Task 2026: Cross-Architecture Ensembling for Punctuation-Free Arabic Segmentation
%A Elmasry, Gaser
%A Elbedewy, Abdulrahman
%A Taha, Abdelrahman Wael Atef
%A Seddik, Fahd
%A Abdelmoniem, Mohamed Ahmed Mohamed
%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 elmasry-etal-2026-faamg
%X Arabic sentence segmentation without punctuation or paragraph boundaries requires models to infer boundaries only from lexical, syntactic, and discourse context. We describe FAAMG’s submission in the closed track of AraSeg 2026 Subtask 4 (NoPnx-NP), restricted to only 174 training documents for fine-tuning. Our system is a weighted ensemble of eight models based on AraBERT, SaT, and CAMeLBERT BiLSTM-CRF. The ensemble covers a variety of regularization, encoder capacity, and sequence modeling. The resulting system achieves 86.7 document-macro F1 on the Blind Test set ranking fourth on the leaderboard. Through leave-one-out ablations we show that the ensemble contributes complementary information over the individual models.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.121/
%P 977-994
Markdown (Informal)
[FAAMG at AraSeg Shared Task 2026: Cross-Architecture Ensembling for Punctuation-Free Arabic Segmentation](https://aclanthology.org/2026.arabicnlp-sharedtasks.121/) (Elmasry et al., ArabicNLP 2026)
ACL