@inproceedings{jauhiainen-etal-2022-italian,
title = "{I}talian Language and Dialect Identification and Regional {F}rench Variety Detection using Adaptive Naive {B}ayes",
author = "Jauhiainen, Tommi and
Jauhiainen, Heidi and
Lind{\'e}n, Krister",
editor = {Scherrer, Yves and
Jauhiainen, Tommi and
Ljube{\v{s}}i{\'c}, Nikola and
Nakov, Preslav and
Tiedemann, J{\"o}rg and
Zampieri, Marcos},
booktitle = "Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.vardial-1.13",
pages = "119--129",
abstract = "This article describes the language identification approach used by the SUKI team in the Identification of Languages and Dialects of Italy and the French Cross-Domain Dialect Identification shared tasks organized as part of the VarDial workshop 2022. We describe some experiments and the preprocessing techniques we used for the training data in preparation for the shared task submissions, which are also discussed. Our Naive Bayes-based adaptive system reached the first position in Italian language identification and came second in the French variety identification task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jauhiainen-etal-2022-italian">
<titleInfo>
<title>Italian Language and Dialect Identification and Regional French Variety Detection using Adaptive Naive Bayes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heidi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krister</namePart>
<namePart type="family">Lindén</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes the language identification approach used by the SUKI team in the Identification of Languages and Dialects of Italy and the French Cross-Domain Dialect Identification shared tasks organized as part of the VarDial workshop 2022. We describe some experiments and the preprocessing techniques we used for the training data in preparation for the shared task submissions, which are also discussed. Our Naive Bayes-based adaptive system reached the first position in Italian language identification and came second in the French variety identification task.</abstract>
<identifier type="citekey">jauhiainen-etal-2022-italian</identifier>
<location>
<url>https://aclanthology.org/2022.vardial-1.13</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>119</start>
<end>129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Italian Language and Dialect Identification and Regional French Variety Detection using Adaptive Naive Bayes
%A Jauhiainen, Tommi
%A Jauhiainen, Heidi
%A Lindén, Krister
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%Y Ljubešić, Nikola
%Y Nakov, Preslav
%Y Tiedemann, Jörg
%Y Zampieri, Marcos
%S Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F jauhiainen-etal-2022-italian
%X This article describes the language identification approach used by the SUKI team in the Identification of Languages and Dialects of Italy and the French Cross-Domain Dialect Identification shared tasks organized as part of the VarDial workshop 2022. We describe some experiments and the preprocessing techniques we used for the training data in preparation for the shared task submissions, which are also discussed. Our Naive Bayes-based adaptive system reached the first position in Italian language identification and came second in the French variety identification task.
%U https://aclanthology.org/2022.vardial-1.13
%P 119-129
Markdown (Informal)
[Italian Language and Dialect Identification and Regional French Variety Detection using Adaptive Naive Bayes](https://aclanthology.org/2022.vardial-1.13) (Jauhiainen et al., VarDial 2022)
ACL