@inproceedings{lichouri-abbas-2020-simple,
title = "Simple vs Oversampling-based Classification Methods for Fine Grained {A}rabic Dialect Identification in {T}witter",
author = "Lichouri, Mohamed and
Abbas, Mourad",
editor = "Zitouni, Imed and
Abdul-Mageed, Muhammad and
Bouamor, Houda and
Bougares, Fethi and
El-Haj, Mahmoud and
Tomeh, Nadi and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fifth Arabic Natural Language Processing Workshop",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wanlp-1.24",
pages = "250--256",
abstract = "In this paper, we present a description of our experiments on country-level Arabic dialect identification. A comparison study between a set of classifiers has been carried out. The best results were achieved using the Linear Support Vector Classification (LSVC) model by applying a Random Over Sampling (ROS) process yielding an F1-score of 18.74{\%} in the post-evaluation phase. In the evaluation phase, our best submitted system has achieved an F1-score of 18.27{\%}, very close to the average F1-score (18.80{\%}) obtained for all the submitted systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lichouri-abbas-2020-simple">
<titleInfo>
<title>Simple vs Oversampling-based Classification Methods for Fine Grained Arabic Dialect Identification in Twitter</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">Mourad</namePart>
<namePart type="family">Abbas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<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">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</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">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</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">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a description of our experiments on country-level Arabic dialect identification. A comparison study between a set of classifiers has been carried out. The best results were achieved using the Linear Support Vector Classification (LSVC) model by applying a Random Over Sampling (ROS) process yielding an F1-score of 18.74% in the post-evaluation phase. In the evaluation phase, our best submitted system has achieved an F1-score of 18.27%, very close to the average F1-score (18.80%) obtained for all the submitted systems.</abstract>
<identifier type="citekey">lichouri-abbas-2020-simple</identifier>
<location>
<url>https://aclanthology.org/2020.wanlp-1.24</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>250</start>
<end>256</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple vs Oversampling-based Classification Methods for Fine Grained Arabic Dialect Identification in Twitter
%A Lichouri, Mohamed
%A Abbas, Mourad
%Y Zitouni, Imed
%Y Abdul-Mageed, Muhammad
%Y Bouamor, Houda
%Y Bougares, Fethi
%Y El-Haj, Mahmoud
%Y Tomeh, Nadi
%Y Zaghouani, Wajdi
%S Proceedings of the Fifth Arabic Natural Language Processing Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F lichouri-abbas-2020-simple
%X In this paper, we present a description of our experiments on country-level Arabic dialect identification. A comparison study between a set of classifiers has been carried out. The best results were achieved using the Linear Support Vector Classification (LSVC) model by applying a Random Over Sampling (ROS) process yielding an F1-score of 18.74% in the post-evaluation phase. In the evaluation phase, our best submitted system has achieved an F1-score of 18.27%, very close to the average F1-score (18.80%) obtained for all the submitted systems.
%U https://aclanthology.org/2020.wanlp-1.24
%P 250-256
Markdown (Informal)
[Simple vs Oversampling-based Classification Methods for Fine Grained Arabic Dialect Identification in Twitter](https://aclanthology.org/2020.wanlp-1.24) (Lichouri & Abbas, WANLP 2020)
ACL