@inproceedings{lichouri-etal-2023-usthb-nadi,
title = "{USTHB} at {NADI} 2023 shared task: Exploring Preprocessing and Feature Engineering Strategies for {A}rabic Dialect Identification",
author = "Lichouri, Mohamed and
Lounnas, Khaled and
Zitouni, Aicha and
Latrache, Houda and
Djeradi, Rachida",
editor = "Sawaf, Hassan and
El-Beltagy, Samhaa and
Zaghouani, Wajdi and
Magdy, Walid and
Abdelali, Ahmed and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Habash, Nizar and
Khalifa, Salam and
Keleg, Amr and
Haddad, Hatem and
Zitouni, Imed and
Mrini, Khalil and
Almatham, Rawan",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.69",
doi = "10.18653/v1/2023.arabicnlp-1.69",
pages = "647--651",
abstract = "In this paper, we conduct an in-depth analysis of several key factors influencing the performance of Arabic Dialect Identification NADI{'}2023, with a specific focus on the first subtask involving country-level dialect identification. Our investigation encompasses the effects of surface preprocessing, morphological preprocessing, FastText vector model, and the weighted concatenation of TF-IDF features. For classification purposes, we employ the Linear Support Vector Classification (LSVC) model. During the evaluation phase, our system demonstrates noteworthy results, achieving an F$_1$ score of 62.51{\%}. This achievement closely aligns with the average F$_1$ scores attained by other systems submitted for the first subtask, which stands at 72.91{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lichouri-etal-2023-usthb-nadi">
<titleInfo>
<title>USTHB at NADI 2023 shared task: Exploring Preprocessing and Feature Engineering Strategies for Arabic Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Lichouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khaled</namePart>
<namePart type="family">Lounnas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aicha</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Latrache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachida</namePart>
<namePart type="family">Djeradi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ArabicNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</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">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</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">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</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">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</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>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we conduct an in-depth analysis of several key factors influencing the performance of Arabic Dialect Identification NADI’2023, with a specific focus on the first subtask involving country-level dialect identification. Our investigation encompasses the effects of surface preprocessing, morphological preprocessing, FastText vector model, and the weighted concatenation of TF-IDF features. For classification purposes, we employ the Linear Support Vector Classification (LSVC) model. During the evaluation phase, our system demonstrates noteworthy results, achieving an F₁ score of 62.51%. This achievement closely aligns with the average F₁ scores attained by other systems submitted for the first subtask, which stands at 72.91%.</abstract>
<identifier type="citekey">lichouri-etal-2023-usthb-nadi</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.69</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.69</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>647</start>
<end>651</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T USTHB at NADI 2023 shared task: Exploring Preprocessing and Feature Engineering Strategies for Arabic Dialect Identification
%A Lichouri, Mohamed
%A Lounnas, Khaled
%A Zitouni, Aicha
%A Latrache, Houda
%A Djeradi, Rachida
%Y Sawaf, Hassan
%Y El-Beltagy, Samhaa
%Y Zaghouani, Wajdi
%Y Magdy, Walid
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Habash, Nizar
%Y Khalifa, Salam
%Y Keleg, Amr
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y Mrini, Khalil
%Y Almatham, Rawan
%S Proceedings of ArabicNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore (Hybrid)
%F lichouri-etal-2023-usthb-nadi
%X In this paper, we conduct an in-depth analysis of several key factors influencing the performance of Arabic Dialect Identification NADI’2023, with a specific focus on the first subtask involving country-level dialect identification. Our investigation encompasses the effects of surface preprocessing, morphological preprocessing, FastText vector model, and the weighted concatenation of TF-IDF features. For classification purposes, we employ the Linear Support Vector Classification (LSVC) model. During the evaluation phase, our system demonstrates noteworthy results, achieving an F₁ score of 62.51%. This achievement closely aligns with the average F₁ scores attained by other systems submitted for the first subtask, which stands at 72.91%.
%R 10.18653/v1/2023.arabicnlp-1.69
%U https://aclanthology.org/2023.arabicnlp-1.69
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.69
%P 647-651
Markdown (Informal)
[USTHB at NADI 2023 shared task: Exploring Preprocessing and Feature Engineering Strategies for Arabic Dialect Identification](https://aclanthology.org/2023.arabicnlp-1.69) (Lichouri et al., ArabicNLP-WS 2023)
ACL