@inproceedings{gugliotta-dinarelli-2022-tarc,
title = "{TA}r{C}: {T}unisian {A}rabish Corpus, First complete release",
author = "Gugliotta, Elisa and
Dinarelli, Marco",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.121",
pages = "1125--1136",
abstract = "In this paper we present the final result of a project focused on Tunisian Arabic encoded in Arabizi, the Latin-based writing system for digital conversations. The project led to the realization of two integrated and independent tools: a linguistic corpus and a neural network architecture created to annotate the former with various levels of linguistic information (code-switching classification, transliteration, tokenization, POS-tagging, lemmatization). We discuss the choices made in terms of computational and linguistic methodology and the strategies adopted to improve our results. We report on the experiments performed in order to outline our research path. Finally, we explain the reasons why we believe in the potential of these tools for both computational and linguistic researches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gugliotta-dinarelli-2022-tarc">
<titleInfo>
<title>TArC: Tunisian Arabish Corpus, First complete release</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>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>In this paper we present the final result of a project focused on Tunisian Arabic encoded in Arabizi, the Latin-based writing system for digital conversations. The project led to the realization of two integrated and independent tools: a linguistic corpus and a neural network architecture created to annotate the former with various levels of linguistic information (code-switching classification, transliteration, tokenization, POS-tagging, lemmatization). We discuss the choices made in terms of computational and linguistic methodology and the strategies adopted to improve our results. We report on the experiments performed in order to outline our research path. Finally, we explain the reasons why we believe in the potential of these tools for both computational and linguistic researches.</abstract>
<identifier type="citekey">gugliotta-dinarelli-2022-tarc</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.121</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1125</start>
<end>1136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TArC: Tunisian Arabish Corpus, First complete release
%A Gugliotta, Elisa
%A Dinarelli, Marco
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F gugliotta-dinarelli-2022-tarc
%X In this paper we present the final result of a project focused on Tunisian Arabic encoded in Arabizi, the Latin-based writing system for digital conversations. The project led to the realization of two integrated and independent tools: a linguistic corpus and a neural network architecture created to annotate the former with various levels of linguistic information (code-switching classification, transliteration, tokenization, POS-tagging, lemmatization). We discuss the choices made in terms of computational and linguistic methodology and the strategies adopted to improve our results. We report on the experiments performed in order to outline our research path. Finally, we explain the reasons why we believe in the potential of these tools for both computational and linguistic researches.
%U https://aclanthology.org/2022.lrec-1.121
%P 1125-1136
Markdown (Informal)
[TArC: Tunisian Arabish Corpus, First complete release](https://aclanthology.org/2022.lrec-1.121) (Gugliotta & Dinarelli, LREC 2022)
ACL