@inproceedings{talafha-etal-2019-team,
title = "Team {JUST} at the {MADAR} Shared Task on {A}rabic Fine-Grained Dialect Identification",
author = "Talafha, Bashar and
Fadel, Ali and
Al-Ayyoub, Mahmoud and
Jararweh, Yaser and
AL-Smadi, Mohammad and
Juola, Patrick",
editor = "El-Hajj, Wassim and
Belguith, Lamia Hadrich and
Bougares, Fethi and
Magdy, Walid and
Zitouni, Imed and
Tomeh, Nadi and
El-Haj, Mahmoud and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fourth Arabic Natural Language Processing Workshop",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4638",
doi = "10.18653/v1/W19-4638",
pages = "285--289",
abstract = "In this paper, we describe our team{'}s effort on the MADAR Shared Task on Arabic Fine-Grained Dialect Identification. The task requires building a system capable of differentiating between 25 different Arabic dialects in addition to MSA. Our approach is simple. After preprocessing the data, we use Data Augmentation (DA) to enlarge the training data six times. We then build a language model and extract n-gram word-level and character-level TF-IDF features and feed them into an MNB classifier. Despite its simplicity, the resulting model performs really well producing the 4th highest F-measure and region-level accuracy and the 5th highest precision, recall, city-level accuracy and country-level accuracy among the participating teams.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="talafha-etal-2019-team">
<titleInfo>
<title>Team JUST at the MADAR Shared Task on Arabic Fine-Grained Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Talafha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Fadel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Al-Ayyoub</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Jararweh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">AL-Smadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Juola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wassim</namePart>
<namePart type="family">El-Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="given">Hadrich</namePart>
<namePart type="family">Belguith</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">Walid</namePart>
<namePart type="family">Magdy</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">Nadi</namePart>
<namePart type="family">Tomeh</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">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">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe our team’s effort on the MADAR Shared Task on Arabic Fine-Grained Dialect Identification. The task requires building a system capable of differentiating between 25 different Arabic dialects in addition to MSA. Our approach is simple. After preprocessing the data, we use Data Augmentation (DA) to enlarge the training data six times. We then build a language model and extract n-gram word-level and character-level TF-IDF features and feed them into an MNB classifier. Despite its simplicity, the resulting model performs really well producing the 4th highest F-measure and region-level accuracy and the 5th highest precision, recall, city-level accuracy and country-level accuracy among the participating teams.</abstract>
<identifier type="citekey">talafha-etal-2019-team</identifier>
<identifier type="doi">10.18653/v1/W19-4638</identifier>
<location>
<url>https://aclanthology.org/W19-4638</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>285</start>
<end>289</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team JUST at the MADAR Shared Task on Arabic Fine-Grained Dialect Identification
%A Talafha, Bashar
%A Fadel, Ali
%A Al-Ayyoub, Mahmoud
%A Jararweh, Yaser
%A AL-Smadi, Mohammad
%A Juola, Patrick
%Y El-Hajj, Wassim
%Y Belguith, Lamia Hadrich
%Y Bougares, Fethi
%Y Magdy, Walid
%Y Zitouni, Imed
%Y Tomeh, Nadi
%Y El-Haj, Mahmoud
%Y Zaghouani, Wajdi
%S Proceedings of the Fourth Arabic Natural Language Processing Workshop
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F talafha-etal-2019-team
%X In this paper, we describe our team’s effort on the MADAR Shared Task on Arabic Fine-Grained Dialect Identification. The task requires building a system capable of differentiating between 25 different Arabic dialects in addition to MSA. Our approach is simple. After preprocessing the data, we use Data Augmentation (DA) to enlarge the training data six times. We then build a language model and extract n-gram word-level and character-level TF-IDF features and feed them into an MNB classifier. Despite its simplicity, the resulting model performs really well producing the 4th highest F-measure and region-level accuracy and the 5th highest precision, recall, city-level accuracy and country-level accuracy among the participating teams.
%R 10.18653/v1/W19-4638
%U https://aclanthology.org/W19-4638
%U https://doi.org/10.18653/v1/W19-4638
%P 285-289
Markdown (Informal)
[Team JUST at the MADAR Shared Task on Arabic Fine-Grained Dialect Identification](https://aclanthology.org/W19-4638) (Talafha et al., WANLP 2019)
ACL