@inproceedings{nasr-etal-2026-comparative,
title = "Comparative Study of Classical {NLP} and Pretrained Language Models for {T}unisian Dialect Processing",
author = "Nasr, Latifa Iben and
Badache, Ismail and
Belguith, Lamia",
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",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-main.22/",
pages = "317--324",
ISBN = "979-8-89176-473-6",
abstract = "Recent transformer-based language models rely on subword tokenization and contextual embeddings, raising questions about the continued effectiveness of traditional preprocessing techniques such as stemming. This issue remains underexplored for low-resource Arabic dialects, particularly Tunisian Dialect (TD). In this paper, we investigate the impact of light and aggressive stemming on two main Tunisian NLP tasks: sentiment analysis and domain classification. We compare classical machine learning methods with transformer-based Arabic language models, including TunBERT. To support this study, we release an open Tunisian stemming resource containing 7,730 words annotated with both light and aggressive stems. Our experiments provide a comprehensive analysis of TD processing and show that the effectiveness of stemming depends on both the task and the model type."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nasr-etal-2026-comparative">
<titleInfo>
<title>Comparative Study of Classical NLP and Pretrained Language Models for Tunisian Dialect Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Latifa</namePart>
<namePart type="given">Iben</namePart>
<namePart type="family">Nasr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ismail</namePart>
<namePart type="family">Badache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="family">Belguith</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</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">979-8-89176-473-6</identifier>
</relatedItem>
<abstract>Recent transformer-based language models rely on subword tokenization and contextual embeddings, raising questions about the continued effectiveness of traditional preprocessing techniques such as stemming. This issue remains underexplored for low-resource Arabic dialects, particularly Tunisian Dialect (TD). In this paper, we investigate the impact of light and aggressive stemming on two main Tunisian NLP tasks: sentiment analysis and domain classification. We compare classical machine learning methods with transformer-based Arabic language models, including TunBERT. To support this study, we release an open Tunisian stemming resource containing 7,730 words annotated with both light and aggressive stems. Our experiments provide a comprehensive analysis of TD processing and show that the effectiveness of stemming depends on both the task and the model type.</abstract>
<identifier type="citekey">nasr-etal-2026-comparative</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.22/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>317</start>
<end>324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparative Study of Classical NLP and Pretrained Language Models for Tunisian Dialect Processing
%A Nasr, Latifa Iben
%A Badache, Ismail
%A Belguith, Lamia
%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
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-473-6
%F nasr-etal-2026-comparative
%X Recent transformer-based language models rely on subword tokenization and contextual embeddings, raising questions about the continued effectiveness of traditional preprocessing techniques such as stemming. This issue remains underexplored for low-resource Arabic dialects, particularly Tunisian Dialect (TD). In this paper, we investigate the impact of light and aggressive stemming on two main Tunisian NLP tasks: sentiment analysis and domain classification. We compare classical machine learning methods with transformer-based Arabic language models, including TunBERT. To support this study, we release an open Tunisian stemming resource containing 7,730 words annotated with both light and aggressive stems. Our experiments provide a comprehensive analysis of TD processing and show that the effectiveness of stemming depends on both the task and the model type.
%U https://aclanthology.org/2026.arabicnlp-main.22/
%P 317-324
Markdown (Informal)
[Comparative Study of Classical NLP and Pretrained Language Models for Tunisian Dialect Processing](https://aclanthology.org/2026.arabicnlp-main.22/) (Nasr et al., ArabicNLP 2026)
ACL