@inproceedings{talafha-etal-2019-mawdoo3,
title = "Mawdoo3 {AI} at {MADAR} Shared Task: {A}rabic Tweet Dialect Identification",
author = "Talafha, Bashar and
Farhan, Wael and
Altakrouri, Ahmed and
Al-Natsheh, Hussein",
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/W19-4629",
doi = "10.18653/v1/W19-4629",
pages = "239--243",
abstract = "Arabic dialect identification is an inherently complex problem, as Arabic dialect taxonomy is convoluted and aims to dissect a continuous space rather than a discrete one. In this work, we present machine and deep learning approaches to predict 21 fine-grained dialects form a set of given tweets per user. We adopted numerous feature extraction methods most of which showed improvement in the final model, such as word embedding, Tf-idf, and other tweet features. Our results show that a simple LinearSVC can outperform any complex deep learning model given a set of curated features. With a relatively complex user voting mechanism, we were able to achieve a Macro-Averaged F1-score of 71.84{\%} on MADAR shared subtask-2. Our best submitted model ranked second out of all participating teams.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="talafha-etal-2019-mawdoo3">
<titleInfo>
<title>Mawdoo3 AI at MADAR Shared Task: Arabic Tweet 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">Wael</namePart>
<namePart type="family">Farhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Altakrouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hussein</namePart>
<namePart type="family">Al-Natsheh</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>Arabic dialect identification is an inherently complex problem, as Arabic dialect taxonomy is convoluted and aims to dissect a continuous space rather than a discrete one. In this work, we present machine and deep learning approaches to predict 21 fine-grained dialects form a set of given tweets per user. We adopted numerous feature extraction methods most of which showed improvement in the final model, such as word embedding, Tf-idf, and other tweet features. Our results show that a simple LinearSVC can outperform any complex deep learning model given a set of curated features. With a relatively complex user voting mechanism, we were able to achieve a Macro-Averaged F1-score of 71.84% on MADAR shared subtask-2. Our best submitted model ranked second out of all participating teams.</abstract>
<identifier type="citekey">talafha-etal-2019-mawdoo3</identifier>
<identifier type="doi">10.18653/v1/W19-4629</identifier>
<location>
<url>https://aclanthology.org/W19-4629</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>239</start>
<end>243</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mawdoo3 AI at MADAR Shared Task: Arabic Tweet Dialect Identification
%A Talafha, Bashar
%A Farhan, Wael
%A Altakrouri, Ahmed
%A Al-Natsheh, Hussein
%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-mawdoo3
%X Arabic dialect identification is an inherently complex problem, as Arabic dialect taxonomy is convoluted and aims to dissect a continuous space rather than a discrete one. In this work, we present machine and deep learning approaches to predict 21 fine-grained dialects form a set of given tweets per user. We adopted numerous feature extraction methods most of which showed improvement in the final model, such as word embedding, Tf-idf, and other tweet features. Our results show that a simple LinearSVC can outperform any complex deep learning model given a set of curated features. With a relatively complex user voting mechanism, we were able to achieve a Macro-Averaged F1-score of 71.84% on MADAR shared subtask-2. Our best submitted model ranked second out of all participating teams.
%R 10.18653/v1/W19-4629
%U https://aclanthology.org/W19-4629
%U https://doi.org/10.18653/v1/W19-4629
%P 239-243
Markdown (Informal)
[Mawdoo3 AI at MADAR Shared Task: Arabic Tweet Dialect Identification](https://aclanthology.org/W19-4629) (Talafha et al., WANLP 2019)
ACL