@inproceedings{iskandar-etal-2026-ai,
title = "{AI} Elites at {NADI} 2026 Shared Task: Selecting on Out-of-Domain Accuracy for Cross-Domain Spoken {A}rabic Dialect Identification",
author = "Iskandar, Musab and
Al-Haig, Mohammed and
Alharbi, Adel Sameer and
Alharbi, Khalid and
Mohamed, Youssef",
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.10/",
pages = "88--94",
ISBN = "979-8-89176-497-2",
abstract = "We describe our submission to NADI-2026 Subtask{~}2, country-level spoken Arabic dialect identification on a blind test set from undisclosed sources. Because the target domain is unknown at development time, we select on out-of-domain accuracy rather than in-domain validation accuracy at every decision point, comparing three backbones under a common pooling-plus-linear head and training the selected Arabic ASR encoder on ADI20-micro mixed with Casablanca. The system reaches 91.54{\%} in-domain, 73.10{\%} on the held-out MADIS-5 corpus (scored five-way), and 52.51{\%} on the blind test set ($C_{\mathrm{avg}}$ 0.11), placing fourth. The criterion helped, choosing an encoder that in-domain accuracy would have rejected by 32 points on a held-out corpus, a gap more than twenty times our measured seed variation, but it was not sufficient: of the 39.03-point in-domain to blind gap, at least 18.44 points are attributable to leaving the training domain. We trace part of the remainder to a corpus that entered the training mixture while still being used for checkpoint selection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iskandar-etal-2026-ai">
<titleInfo>
<title>AI Elites at NADI 2026 Shared Task: Selecting on Out-of-Domain Accuracy for Cross-Domain Spoken Arabic Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Musab</namePart>
<namePart type="family">Iskandar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Al-Haig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adel</namePart>
<namePart type="given">Sameer</namePart>
<namePart type="family">Alharbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alharbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youssef</namePart>
<namePart type="family">Mohamed</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>We describe our submission to NADI-2026 Subtask 2, country-level spoken Arabic dialect identification on a blind test set from undisclosed sources. Because the target domain is unknown at development time, we select on out-of-domain accuracy rather than in-domain validation accuracy at every decision point, comparing three backbones under a common pooling-plus-linear head and training the selected Arabic ASR encoder on ADI20-micro mixed with Casablanca. The system reaches 91.54% in-domain, 73.10% on the held-out MADIS-5 corpus (scored five-way), and 52.51% on the blind test set (C_avg 0.11), placing fourth. The criterion helped, choosing an encoder that in-domain accuracy would have rejected by 32 points on a held-out corpus, a gap more than twenty times our measured seed variation, but it was not sufficient: of the 39.03-point in-domain to blind gap, at least 18.44 points are attributable to leaving the training domain. We trace part of the remainder to a corpus that entered the training mixture while still being used for checkpoint selection.</abstract>
<identifier type="citekey">iskandar-etal-2026-ai</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.10/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>88</start>
<end>94</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T AI Elites at NADI 2026 Shared Task: Selecting on Out-of-Domain Accuracy for Cross-Domain Spoken Arabic Dialect Identification %A Iskandar, Musab %A Al-Haig, Mohammed %A Alharbi, Adel Sameer %A Alharbi, Khalid %A Mohamed, Youssef %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 iskandar-etal-2026-ai %X We describe our submission to NADI-2026 Subtask 2, country-level spoken Arabic dialect identification on a blind test set from undisclosed sources. Because the target domain is unknown at development time, we select on out-of-domain accuracy rather than in-domain validation accuracy at every decision point, comparing three backbones under a common pooling-plus-linear head and training the selected Arabic ASR encoder on ADI20-micro mixed with Casablanca. The system reaches 91.54% in-domain, 73.10% on the held-out MADIS-5 corpus (scored five-way), and 52.51% on the blind test set (C_avg 0.11), placing fourth. The criterion helped, choosing an encoder that in-domain accuracy would have rejected by 32 points on a held-out corpus, a gap more than twenty times our measured seed variation, but it was not sufficient: of the 39.03-point in-domain to blind gap, at least 18.44 points are attributable to leaving the training domain. We trace part of the remainder to a corpus that entered the training mixture while still being used for checkpoint selection. %U https://aclanthology.org/2026.arabicnlp-sharedtasks.10/ %P 88-94
Markdown (Informal)
[AI Elites at NADI 2026 Shared Task: Selecting on Out-of-Domain Accuracy for Cross-Domain Spoken Arabic Dialect Identification](https://aclanthology.org/2026.arabicnlp-sharedtasks.10/) (Iskandar et al., ArabicNLP 2026)