@inproceedings{nayel-etal-2021-machine,
title = "Machine Learning-Based Approach for {A}rabic Dialect Identification",
author = "Nayel, Hamada and
Hassan, Ahmed and
Sobhi, Mahmoud and
El-Sawy, Ahmed",
booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
month = apr,
year = "2021",
address = "Kyiv, Ukraine (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wanlp-1.34",
pages = "287--290",
abstract = {This paper describes our systems submitted to the Second Nuanced Arabic Dialect Identification Shared Task (NADI 2021). Dialect identification is the task of automatically detecting the source variety of a given text or speech segment. There are four subtasks, two subtasks for country-level identification and the other two subtasks for province-level identification. The data in this task covers a total of 100 provinces from all 21 Arab countries and come from the Twitter domain. The proposed systems depend on five machine-learning approaches namely Complement Na{\"\i}ve Bayes, Support Vector Machine, Decision Tree, Logistic Regression and Random Forest Classifiers. F1 macro-averaged score of Na{\"\i}ve Bayes classifier outperformed all other classifiers for development and test data.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nayel-etal-2021-machine">
<titleInfo>
<title>Machine Learning-Based Approach for Arabic Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hamada</namePart>
<namePart type="family">Nayel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Sobhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">El-Sawy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-apr</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our systems submitted to the Second Nuanced Arabic Dialect Identification Shared Task (NADI 2021). Dialect identification is the task of automatically detecting the source variety of a given text or speech segment. There are four subtasks, two subtasks for country-level identification and the other two subtasks for province-level identification. The data in this task covers a total of 100 provinces from all 21 Arab countries and come from the Twitter domain. The proposed systems depend on five machine-learning approaches namely Complement Naïve Bayes, Support Vector Machine, Decision Tree, Logistic Regression and Random Forest Classifiers. F1 macro-averaged score of Naïve Bayes classifier outperformed all other classifiers for development and test data.</abstract>
<identifier type="citekey">nayel-etal-2021-machine</identifier>
<location>
<url>https://aclanthology.org/2021.wanlp-1.34</url>
</location>
<part>
<date>2021-apr</date>
<extent unit="page">
<start>287</start>
<end>290</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Learning-Based Approach for Arabic Dialect Identification
%A Nayel, Hamada
%A Hassan, Ahmed
%A Sobhi, Mahmoud
%A El-Sawy, Ahmed
%S Proceedings of the Sixth Arabic Natural Language Processing Workshop
%D 2021
%8 apr
%I Association for Computational Linguistics
%C Kyiv, Ukraine (Virtual)
%F nayel-etal-2021-machine
%X This paper describes our systems submitted to the Second Nuanced Arabic Dialect Identification Shared Task (NADI 2021). Dialect identification is the task of automatically detecting the source variety of a given text or speech segment. There are four subtasks, two subtasks for country-level identification and the other two subtasks for province-level identification. The data in this task covers a total of 100 provinces from all 21 Arab countries and come from the Twitter domain. The proposed systems depend on five machine-learning approaches namely Complement Naïve Bayes, Support Vector Machine, Decision Tree, Logistic Regression and Random Forest Classifiers. F1 macro-averaged score of Naïve Bayes classifier outperformed all other classifiers for development and test data.
%U https://aclanthology.org/2021.wanlp-1.34
%P 287-290
Markdown (Informal)
[Machine Learning-Based Approach for Arabic Dialect Identification](https://aclanthology.org/2021.wanlp-1.34) (Nayel et al., WANLP 2021)
ACL