@inproceedings{gugliotta-dinarelli-2020-tarc,
title = "{TA}r{C}. Un corpus d{'}arabish tunisien",
author = "Gugliotta, Elisa and
Dinarelli, Marco",
editor = "Benzitoun, Christophe and
Braud, Chlo{\'e} and
Huber, Laurine and
Langlois, David and
Ouni, Slim and
Pogodalla, Sylvain and
Schneider, St{\'e}phane",
booktitle = "Actes de la 6e conf{\'e}rence conjointe Journ{\'e}es d'{\'E}tudes sur la Parole (JEP, 33e {\'e}dition), Traitement Automatique des Langues Naturelles (TALN, 27e {\'e}dition), Rencontre des {\'E}tudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (R{\'E}CITAL, 22e {\'e}dition). Volume 2 : Traitement Automatique des Langues Naturelles",
month = "6",
year = "2020",
address = "Nancy, France",
publisher = "ATALA et AFCP",
url = "https://aclanthology.org/2020.jeptalnrecital-taln.22",
pages = "232--240",
abstract = "TArC : Incrementally and Semi-Automatically Collecting a Tunisian arabish Corpus This article describes the collection process of the first morpho-syntactically annotated Tunisian arabish Corpus (TArC). Arabish is a spontaneous coding of Arabic Dialects (AD) in Latin characters and arithmographs (numbers used as letters). This code-system was developed by Arabic-speaking users of social media in order to facilitate the communication on digital devices. Arabish differs for each Arabic dialect and each arabish code-system is under-resourced. In the last few years, the attention of NLP on AD has considerably increased. TArC will be thus a useful support for different types of analyses, as well as for NLP tools training. In this article we will describe preliminary work on the TArC semi-automatic construction process and some of the first analyses on the corpus. In order to provide a complete overview of the challenges faced during the building process, we will present the main Tunisian dialect characteristics and its encoding in Tunisian arabish.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gugliotta-dinarelli-2020-tarc">
<titleInfo>
<title>TArC. Un corpus d’arabish tunisien</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Gugliotta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Dinarelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes de la 6e conférence conjointe Journées d’Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 2 : Traitement Automatique des Langues Naturelles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Benzitoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chloé</namePart>
<namePart type="family">Braud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurine</namePart>
<namePart type="family">Huber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Langlois</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slim</namePart>
<namePart type="family">Ouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvain</namePart>
<namePart type="family">Pogodalla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stéphane</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA et AFCP</publisher>
<place>
<placeTerm type="text">Nancy, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>TArC : Incrementally and Semi-Automatically Collecting a Tunisian arabish Corpus This article describes the collection process of the first morpho-syntactically annotated Tunisian arabish Corpus (TArC). Arabish is a spontaneous coding of Arabic Dialects (AD) in Latin characters and arithmographs (numbers used as letters). This code-system was developed by Arabic-speaking users of social media in order to facilitate the communication on digital devices. Arabish differs for each Arabic dialect and each arabish code-system is under-resourced. In the last few years, the attention of NLP on AD has considerably increased. TArC will be thus a useful support for different types of analyses, as well as for NLP tools training. In this article we will describe preliminary work on the TArC semi-automatic construction process and some of the first analyses on the corpus. In order to provide a complete overview of the challenges faced during the building process, we will present the main Tunisian dialect characteristics and its encoding in Tunisian arabish.</abstract>
<identifier type="citekey">gugliotta-dinarelli-2020-tarc</identifier>
<location>
<url>https://aclanthology.org/2020.jeptalnrecital-taln.22</url>
</location>
<part>
<date>2020-6</date>
<extent unit="page">
<start>232</start>
<end>240</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TArC. Un corpus d’arabish tunisien
%A Gugliotta, Elisa
%A Dinarelli, Marco
%Y Benzitoun, Christophe
%Y Braud, Chloé
%Y Huber, Laurine
%Y Langlois, David
%Y Ouni, Slim
%Y Pogodalla, Sylvain
%Y Schneider, Stéphane
%S Actes de la 6e conférence conjointe Journées d’Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 2 : Traitement Automatique des Langues Naturelles
%D 2020
%8 June
%I ATALA et AFCP
%C Nancy, France
%F gugliotta-dinarelli-2020-tarc
%X TArC : Incrementally and Semi-Automatically Collecting a Tunisian arabish Corpus This article describes the collection process of the first morpho-syntactically annotated Tunisian arabish Corpus (TArC). Arabish is a spontaneous coding of Arabic Dialects (AD) in Latin characters and arithmographs (numbers used as letters). This code-system was developed by Arabic-speaking users of social media in order to facilitate the communication on digital devices. Arabish differs for each Arabic dialect and each arabish code-system is under-resourced. In the last few years, the attention of NLP on AD has considerably increased. TArC will be thus a useful support for different types of analyses, as well as for NLP tools training. In this article we will describe preliminary work on the TArC semi-automatic construction process and some of the first analyses on the corpus. In order to provide a complete overview of the challenges faced during the building process, we will present the main Tunisian dialect characteristics and its encoding in Tunisian arabish.
%U https://aclanthology.org/2020.jeptalnrecital-taln.22
%P 232-240
Markdown (Informal)
[TArC. Un corpus d’arabish tunisien](https://aclanthology.org/2020.jeptalnrecital-taln.22) (Gugliotta & Dinarelli, JEP/TALN/RECITAL 2020)
ACL
- Elisa Gugliotta and Marco Dinarelli. 2020. TArC. Un corpus d’arabish tunisien. In Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 2 : Traitement Automatique des Langues Naturelles, pages 232–240, Nancy, France. ATALA et AFCP.