@inproceedings{yassine-bichi-2026-codezone,
title = "{C}ode{Z}one Research Group at {NADI} 2026 Shared Task: Cross-Domain Score Calibration for Spoken {A}rabic Dialect Identification",
author = "Yassine, Sarah and
Bichi, Abdulkadir Shehu",
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.9/",
pages = "79--87",
ISBN = "979-8-89176-497-2",
abstract = "We describe the CodeZone Research Group system for NADI 2026 Shared Task 2, spo ken Arabic dialect identification over Modern Standard Arabic and 19 country-level dialects under cross-domain evaluation. Our system ensembles an ECAPA-TDNN language identi fier fine-tuned on the shared task data with a Whisper-large-v3 dialect classifier that we fur ther adapt using waveform- and spectrogram level augmentation, fusing their log-softmax scores. This ensemble reaches 94.35{\%} accu racy on in-domain validation but initially re tained only 25.40{\%} on the official blind test, a collapse that affected every participating team. We show that about a fifth of this gap is a cali bration failure rather than a modelling failure: discarding per-class bias terms fit in domain raised official accuracy from 0.2540 to 0.3918 and lowered the shared task{'}s average cost from 0.2077 to 0.1515, and a softening temperature reduced cost further to 0.1469; neither change touched either model. Our submission ranked 10th of 16 teams, and we show analytically why uniform additive score shifts cannot affect this metric while temperature scaling can."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yassine-bichi-2026-codezone">
<titleInfo>
<title>CodeZone Research Group at NADI 2026 Shared Task: Cross-Domain Score Calibration for Spoken Arabic Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Yassine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulkadir</namePart>
<namePart type="given">Shehu</namePart>
<namePart type="family">Bichi</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 the CodeZone Research Group system for NADI 2026 Shared Task 2, spo ken Arabic dialect identification over Modern Standard Arabic and 19 country-level dialects under cross-domain evaluation. Our system ensembles an ECAPA-TDNN language identi fier fine-tuned on the shared task data with a Whisper-large-v3 dialect classifier that we fur ther adapt using waveform- and spectrogram level augmentation, fusing their log-softmax scores. This ensemble reaches 94.35% accu racy on in-domain validation but initially re tained only 25.40% on the official blind test, a collapse that affected every participating team. We show that about a fifth of this gap is a cali bration failure rather than a modelling failure: discarding per-class bias terms fit in domain raised official accuracy from 0.2540 to 0.3918 and lowered the shared task’s average cost from 0.2077 to 0.1515, and a softening temperature reduced cost further to 0.1469; neither change touched either model. Our submission ranked 10th of 16 teams, and we show analytically why uniform additive score shifts cannot affect this metric while temperature scaling can.</abstract>
<identifier type="citekey">yassine-bichi-2026-codezone</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.9/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>79</start>
<end>87</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CodeZone Research Group at NADI 2026 Shared Task: Cross-Domain Score Calibration for Spoken Arabic Dialect Identification
%A Yassine, Sarah
%A Bichi, Abdulkadir Shehu
%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 yassine-bichi-2026-codezone
%X We describe the CodeZone Research Group system for NADI 2026 Shared Task 2, spo ken Arabic dialect identification over Modern Standard Arabic and 19 country-level dialects under cross-domain evaluation. Our system ensembles an ECAPA-TDNN language identi fier fine-tuned on the shared task data with a Whisper-large-v3 dialect classifier that we fur ther adapt using waveform- and spectrogram level augmentation, fusing their log-softmax scores. This ensemble reaches 94.35% accu racy on in-domain validation but initially re tained only 25.40% on the official blind test, a collapse that affected every participating team. We show that about a fifth of this gap is a cali bration failure rather than a modelling failure: discarding per-class bias terms fit in domain raised official accuracy from 0.2540 to 0.3918 and lowered the shared task’s average cost from 0.2077 to 0.1515, and a softening temperature reduced cost further to 0.1469; neither change touched either model. Our submission ranked 10th of 16 teams, and we show analytically why uniform additive score shifts cannot affect this metric while temperature scaling can.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.9/
%P 79-87
Markdown (Informal)
[CodeZone Research Group at NADI 2026 Shared Task: Cross-Domain Score Calibration for Spoken Arabic Dialect Identification](https://aclanthology.org/2026.arabicnlp-sharedtasks.9/) (Yassine & Bichi, ArabicNLP 2026)
ACL