@inproceedings{hegazy-2026-cis,
title = "{CIS}-{O}pen{SLU} at {NADI} 2026 Shared Task: {ASR}-Matched Training and Confidence-Based Rejection for Open-Set {T}unisian {A}rabic Intent Recognition",
author = "Hegazy, Salma Khaled",
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.8/",
pages = "72--78",
ISBN = "979-8-89176-497-2",
abstract = "Open-set spoken intent recognition for low-resource Arabic varieties must handle both automatic speech recognition (ASR) errors and intents absent from training. We describe CIS-OpenSLU, our NADI 2026 Task 5.1 system, which transcribes Tunisian Arabic speech with Whisper Turbo and classifies the resulting text using word- and character-level TF{--}IDF features with a LinearSVC. On ASR-transcribed validation audio, training the classifier on Whisper-generated transcripts rather than gold transcripts raises weighted F1 from 49.25{\%} to 69.78{\%}, showing that matching training and inference text distributions is crucial. We rank test utterances by the maximum SVM decision score and reject low-confidence examples as unknown; the final system achieves 71.54{\%} weighted F1 and 72.50{\%} accuracy, ranking second. Auxiliary audio and multi-modal experiments further show that strong unseen-intent detection in leave-one-intent-out simulation does not necessarily transfer to genuinely unseen test intents."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hegazy-2026-cis">
<titleInfo>
<title>CIS-OpenSLU at NADI 2026 Shared Task: ASR-Matched Training and Confidence-Based Rejection for Open-Set Tunisian Arabic Intent Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Salma</namePart>
<namePart type="given">Khaled</namePart>
<namePart type="family">Hegazy</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>Open-set spoken intent recognition for low-resource Arabic varieties must handle both automatic speech recognition (ASR) errors and intents absent from training. We describe CIS-OpenSLU, our NADI 2026 Task 5.1 system, which transcribes Tunisian Arabic speech with Whisper Turbo and classifies the resulting text using word- and character-level TF–IDF features with a LinearSVC. On ASR-transcribed validation audio, training the classifier on Whisper-generated transcripts rather than gold transcripts raises weighted F1 from 49.25% to 69.78%, showing that matching training and inference text distributions is crucial. We rank test utterances by the maximum SVM decision score and reject low-confidence examples as unknown; the final system achieves 71.54% weighted F1 and 72.50% accuracy, ranking second. Auxiliary audio and multi-modal experiments further show that strong unseen-intent detection in leave-one-intent-out simulation does not necessarily transfer to genuinely unseen test intents.</abstract>
<identifier type="citekey">hegazy-2026-cis</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.8/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>72</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CIS-OpenSLU at NADI 2026 Shared Task: ASR-Matched Training and Confidence-Based Rejection for Open-Set Tunisian Arabic Intent Recognition
%A Hegazy, Salma Khaled
%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 hegazy-2026-cis
%X Open-set spoken intent recognition for low-resource Arabic varieties must handle both automatic speech recognition (ASR) errors and intents absent from training. We describe CIS-OpenSLU, our NADI 2026 Task 5.1 system, which transcribes Tunisian Arabic speech with Whisper Turbo and classifies the resulting text using word- and character-level TF–IDF features with a LinearSVC. On ASR-transcribed validation audio, training the classifier on Whisper-generated transcripts rather than gold transcripts raises weighted F1 from 49.25% to 69.78%, showing that matching training and inference text distributions is crucial. We rank test utterances by the maximum SVM decision score and reject low-confidence examples as unknown; the final system achieves 71.54% weighted F1 and 72.50% accuracy, ranking second. Auxiliary audio and multi-modal experiments further show that strong unseen-intent detection in leave-one-intent-out simulation does not necessarily transfer to genuinely unseen test intents.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.8/
%P 72-78
Markdown (Informal)
[CIS-OpenSLU at NADI 2026 Shared Task: ASR-Matched Training and Confidence-Based Rejection for Open-Set Tunisian Arabic Intent Recognition](https://aclanthology.org/2026.arabicnlp-sharedtasks.8/) (Hegazy, ArabicNLP 2026)
ACL