@inproceedings{kchaou-etal-2022-standardisation,
title = "Standardisation of Dialect Comments in Social Networks in View of Sentiment Analysis : Case of {T}unisian Dialect",
author = "Kchaou, Sam{\'e}h and
Boujelbane, Rahma and
Fsih, Emna and
Hadrich-Belguith, Lamia",
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-1.582",
pages = "5436--5443",
abstract = "With the growing access to the internet, the spoken Arabic dialect language becomes informal languages written in social media. Most users post comments using their own dialect. This linguistic situation inhibits mutual understanding between internet users and makes difficult to use computational approaches since most Arabic resources are intended for the formal language: Modern Standard Arabic (MSA). In this paper, we present a pipeline to standardize the written texts in social networks by translating them to the standard language MSA. We fine-tun at first an identification bert-based model to select Tunisian Dialect (TD) from MSA and other dialects. Then, we learned transformer model to translate TD to MSA. The final system includes the translated TD text and the originally text written in MSA. Each of these steps was evaluated on the same test corpus. In order to test the effectiveness of the approach, we compared two opinion analysis models, the first intended for the Sentiment Analysis (SA) of dialect texts and the second for the MSA texts. We concluded that through standardization we obtain the best score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kchaou-etal-2022-standardisation">
<titleInfo>
<title>Standardisation of Dialect Comments in Social Networks in View of Sentiment Analysis : Case of Tunisian Dialect</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saméh</namePart>
<namePart type="family">Kchaou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahma</namePart>
<namePart type="family">Boujelbane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emna</namePart>
<namePart type="family">Fsih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="family">Hadrich-Belguith</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>With the growing access to the internet, the spoken Arabic dialect language becomes informal languages written in social media. Most users post comments using their own dialect. This linguistic situation inhibits mutual understanding between internet users and makes difficult to use computational approaches since most Arabic resources are intended for the formal language: Modern Standard Arabic (MSA). In this paper, we present a pipeline to standardize the written texts in social networks by translating them to the standard language MSA. We fine-tun at first an identification bert-based model to select Tunisian Dialect (TD) from MSA and other dialects. Then, we learned transformer model to translate TD to MSA. The final system includes the translated TD text and the originally text written in MSA. Each of these steps was evaluated on the same test corpus. In order to test the effectiveness of the approach, we compared two opinion analysis models, the first intended for the Sentiment Analysis (SA) of dialect texts and the second for the MSA texts. We concluded that through standardization we obtain the best score.</abstract>
<identifier type="citekey">kchaou-etal-2022-standardisation</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.582</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5436</start>
<end>5443</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Standardisation of Dialect Comments in Social Networks in View of Sentiment Analysis : Case of Tunisian Dialect
%A Kchaou, Saméh
%A Boujelbane, Rahma
%A Fsih, Emna
%A Hadrich-Belguith, Lamia
%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 kchaou-etal-2022-standardisation
%X With the growing access to the internet, the spoken Arabic dialect language becomes informal languages written in social media. Most users post comments using their own dialect. This linguistic situation inhibits mutual understanding between internet users and makes difficult to use computational approaches since most Arabic resources are intended for the formal language: Modern Standard Arabic (MSA). In this paper, we present a pipeline to standardize the written texts in social networks by translating them to the standard language MSA. We fine-tun at first an identification bert-based model to select Tunisian Dialect (TD) from MSA and other dialects. Then, we learned transformer model to translate TD to MSA. The final system includes the translated TD text and the originally text written in MSA. Each of these steps was evaluated on the same test corpus. In order to test the effectiveness of the approach, we compared two opinion analysis models, the first intended for the Sentiment Analysis (SA) of dialect texts and the second for the MSA texts. We concluded that through standardization we obtain the best score.
%U https://aclanthology.org/2022.lrec-1.582
%P 5436-5443
Markdown (Informal)
[Standardisation of Dialect Comments in Social Networks in View of Sentiment Analysis : Case of Tunisian Dialect](https://aclanthology.org/2022.lrec-1.582) (Kchaou et al., LREC 2022)
ACL