@inproceedings{el-haj-2020-habibi,
title = "Habibi - a multi Dialect multi National {A}rabic Song Lyrics Corpus",
author = "El-Haj, Mahmoud",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.165/",
pages = "1318--1326",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "This paper introduces Habibi the first Arabic Song Lyrics corpus. The corpus comprises more than 30,000 Arabic song lyrics in 6 Arabic dialects for singers from 18 different Arabic countries. The lyrics are segmented into more than 500,000 sentences (song verses) with more than 3.5 million words. I provide the corpus in both comma separated value (csv) and annotated plain text (txt) file formats. In addition, I converted the csv version into JavaScript Object Notation (json) and eXtensible Markup Language (xml) file formats. To experiment with the corpus I run extensive binary and multi-class experiments for dialect and country-of-origin identification. The identification tasks include the use of several classical machine learning and deep learning models utilising different word embeddings. For the binary dialect identification task the best performing classifier achieved a testing accuracy of 93{\%}. This was achieved using a word-based Convolutional Neural Network (CNN) utilising a Continuous Bag of Words (CBOW) word embeddings model. The results overall show all classical and deep learning models to outperform our baseline, which demonstrates the suitability of the corpus for both dialect and country-of-origin identification tasks. I am making the corpus and the trained CBOW word embeddings freely available for research purposes."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-haj-2020-habibi">
<titleInfo>
<title>Habibi - a multi Dialect multi National Arabic Song Lyrics Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>This paper introduces Habibi the first Arabic Song Lyrics corpus. The corpus comprises more than 30,000 Arabic song lyrics in 6 Arabic dialects for singers from 18 different Arabic countries. The lyrics are segmented into more than 500,000 sentences (song verses) with more than 3.5 million words. I provide the corpus in both comma separated value (csv) and annotated plain text (txt) file formats. In addition, I converted the csv version into JavaScript Object Notation (json) and eXtensible Markup Language (xml) file formats. To experiment with the corpus I run extensive binary and multi-class experiments for dialect and country-of-origin identification. The identification tasks include the use of several classical machine learning and deep learning models utilising different word embeddings. For the binary dialect identification task the best performing classifier achieved a testing accuracy of 93%. This was achieved using a word-based Convolutional Neural Network (CNN) utilising a Continuous Bag of Words (CBOW) word embeddings model. The results overall show all classical and deep learning models to outperform our baseline, which demonstrates the suitability of the corpus for both dialect and country-of-origin identification tasks. I am making the corpus and the trained CBOW word embeddings freely available for research purposes.</abstract>
<identifier type="citekey">el-haj-2020-habibi</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.165/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1318</start>
<end>1326</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Habibi - a multi Dialect multi National Arabic Song Lyrics Corpus
%A El-Haj, Mahmoud
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F el-haj-2020-habibi
%X This paper introduces Habibi the first Arabic Song Lyrics corpus. The corpus comprises more than 30,000 Arabic song lyrics in 6 Arabic dialects for singers from 18 different Arabic countries. The lyrics are segmented into more than 500,000 sentences (song verses) with more than 3.5 million words. I provide the corpus in both comma separated value (csv) and annotated plain text (txt) file formats. In addition, I converted the csv version into JavaScript Object Notation (json) and eXtensible Markup Language (xml) file formats. To experiment with the corpus I run extensive binary and multi-class experiments for dialect and country-of-origin identification. The identification tasks include the use of several classical machine learning and deep learning models utilising different word embeddings. For the binary dialect identification task the best performing classifier achieved a testing accuracy of 93%. This was achieved using a word-based Convolutional Neural Network (CNN) utilising a Continuous Bag of Words (CBOW) word embeddings model. The results overall show all classical and deep learning models to outperform our baseline, which demonstrates the suitability of the corpus for both dialect and country-of-origin identification tasks. I am making the corpus and the trained CBOW word embeddings freely available for research purposes.
%U https://aclanthology.org/2020.lrec-1.165/
%P 1318-1326
Markdown (Informal)
[Habibi - a multi Dialect multi National Arabic Song Lyrics Corpus](https://aclanthology.org/2020.lrec-1.165/) (El-Haj, LREC 2020)
ACL