@inproceedings{mansour-etal-2020-arabic,
title = "{A}rabic Dialect Identification Using {BERT} Fine-Tuning",
author = "Mansour, Moataz and
Tohamy, Moustafa and
Ezzat, Zeyad and
Torki, Marwan",
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-1.33",
pages = "308--312",
abstract = "In the last few years, deep learning has proved to be a very effective paradigm to discover patterns in large data sets. Unfortunately, deep learning training on small data sets is not the best option because most of the time traditional machine learning algorithms could get better scores. Now, we can train the neural network on a large data set then fine-tune on a smaller data set using the transfer learning technique. In this paper, we present our system for NADI shared Task: Country-level Dialect Identification, Our system is based on fine-tuning of BERT and it achieves 22.85 F1-score on Test Set and our rank is 5th out of 18 teams.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mansour-etal-2020-arabic">
<titleInfo>
<title>Arabic Dialect Identification Using BERT Fine-Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Moataz</namePart>
<namePart type="family">Mansour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moustafa</namePart>
<namePart type="family">Tohamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeyad</namePart>
<namePart type="family">Ezzat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marwan</namePart>
<namePart type="family">Torki</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 the last few years, deep learning has proved to be a very effective paradigm to discover patterns in large data sets. Unfortunately, deep learning training on small data sets is not the best option because most of the time traditional machine learning algorithms could get better scores. Now, we can train the neural network on a large data set then fine-tune on a smaller data set using the transfer learning technique. In this paper, we present our system for NADI shared Task: Country-level Dialect Identification, Our system is based on fine-tuning of BERT and it achieves 22.85 F1-score on Test Set and our rank is 5th out of 18 teams.</abstract>
<identifier type="citekey">mansour-etal-2020-arabic</identifier>
<location>
<url>https://aclanthology.org/2020.wanlp-1.33</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>308</start>
<end>312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Dialect Identification Using BERT Fine-Tuning
%A Mansour, Moataz
%A Tohamy, Moustafa
%A Ezzat, Zeyad
%A Torki, Marwan
%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 mansour-etal-2020-arabic
%X In the last few years, deep learning has proved to be a very effective paradigm to discover patterns in large data sets. Unfortunately, deep learning training on small data sets is not the best option because most of the time traditional machine learning algorithms could get better scores. Now, we can train the neural network on a large data set then fine-tune on a smaller data set using the transfer learning technique. In this paper, we present our system for NADI shared Task: Country-level Dialect Identification, Our system is based on fine-tuning of BERT and it achieves 22.85 F1-score on Test Set and our rank is 5th out of 18 teams.
%U https://aclanthology.org/2020.wanlp-1.33
%P 308-312
Markdown (Informal)
[Arabic Dialect Identification Using BERT Fine-Tuning](https://aclanthology.org/2020.wanlp-1.33) (Mansour et al., WANLP 2020)
ACL
- Moataz Mansour, Moustafa Tohamy, Zeyad Ezzat, and Marwan Torki. 2020. Arabic Dialect Identification Using BERT Fine-Tuning. In Proceedings of the Fifth Arabic Natural Language Processing Workshop, pages 308–312, Barcelona, Spain (Online). Association for Computational Linguistics.