@inproceedings{mishra-mujadia-2019-arabic,
title = "{A}rabic Dialect Identification for Travel and {T}witter Text",
author = "Mishra, Pruthwik and
Mujadia, Vandan",
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/W19-4628",
doi = "10.18653/v1/W19-4628",
pages = "234--238",
abstract = "This paper presents the results of the experiments done as a part of MADAR Shared Task in WANLP 2019 on Arabic Fine-Grained Dialect Identification. Dialect Identification is one of the prominent tasks in the field of Natural language processing where the subsequent language modules can be improved based on it. We explored the use of different features like char, word n-gram, language model probabilities, etc on different classifiers. Results show that these features help to improve dialect classification accuracy. Results also show that traditional machine learning classifier tends to perform better when compared to neural network models on this task in a low resource setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mishra-mujadia-2019-arabic">
<titleInfo>
<title>Arabic Dialect Identification for Travel and Twitter Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pruthwik</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vandan</namePart>
<namePart type="family">Mujadia</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>This paper presents the results of the experiments done as a part of MADAR Shared Task in WANLP 2019 on Arabic Fine-Grained Dialect Identification. Dialect Identification is one of the prominent tasks in the field of Natural language processing where the subsequent language modules can be improved based on it. We explored the use of different features like char, word n-gram, language model probabilities, etc on different classifiers. Results show that these features help to improve dialect classification accuracy. Results also show that traditional machine learning classifier tends to perform better when compared to neural network models on this task in a low resource setting.</abstract>
<identifier type="citekey">mishra-mujadia-2019-arabic</identifier>
<identifier type="doi">10.18653/v1/W19-4628</identifier>
<location>
<url>https://aclanthology.org/W19-4628</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>234</start>
<end>238</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Dialect Identification for Travel and Twitter Text
%A Mishra, Pruthwik
%A Mujadia, Vandan
%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 mishra-mujadia-2019-arabic
%X This paper presents the results of the experiments done as a part of MADAR Shared Task in WANLP 2019 on Arabic Fine-Grained Dialect Identification. Dialect Identification is one of the prominent tasks in the field of Natural language processing where the subsequent language modules can be improved based on it. We explored the use of different features like char, word n-gram, language model probabilities, etc on different classifiers. Results show that these features help to improve dialect classification accuracy. Results also show that traditional machine learning classifier tends to perform better when compared to neural network models on this task in a low resource setting.
%R 10.18653/v1/W19-4628
%U https://aclanthology.org/W19-4628
%U https://doi.org/10.18653/v1/W19-4628
%P 234-238
Markdown (Informal)
[Arabic Dialect Identification for Travel and Twitter Text](https://aclanthology.org/W19-4628) (Mishra & Mujadia, WANLP 2019)
ACL