@inproceedings{jauhiainen-etal-2021-naive,
title = "Naive {B}ayes-based Experiments in {R}omanian Dialect Identification",
author = "Jauhiainen, Tommi and
Jauhiainen, Heidi and
Lind{\'e}n, Krister",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Scherrer, Yves and
Jauhiainen, Tommi},
booktitle = "Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects",
month = apr,
year = "2021",
address = "Kiyv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.vardial-1.9",
pages = "76--83",
abstract = "This article describes the experiments and systems developed by the SUKI team for the second edition of the Romanian Dialect Identification (RDI) shared task which was organized as part of the 2021 VarDial Evaluation Campaign. We submitted two runs to the shared task and our second submission was the overall best submission by a noticeable margin. Our best submission used a character n-gram based naive Bayes classifier with adaptive language models. We describe our experiments on the development set leading to both submissions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jauhiainen-etal-2021-naive">
<titleInfo>
<title>Naive Bayes-based Experiments in Romanian Dialect Identification</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>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</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">Nikola</namePart>
<namePart type="family">Ljubešić</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">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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kiyv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes the experiments and systems developed by the SUKI team for the second edition of the Romanian Dialect Identification (RDI) shared task which was organized as part of the 2021 VarDial Evaluation Campaign. We submitted two runs to the shared task and our second submission was the overall best submission by a noticeable margin. Our best submission used a character n-gram based naive Bayes classifier with adaptive language models. We describe our experiments on the development set leading to both submissions.</abstract>
<identifier type="citekey">jauhiainen-etal-2021-naive</identifier>
<location>
<url>https://aclanthology.org/2021.vardial-1.9</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>76</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Naive Bayes-based Experiments in Romanian Dialect Identification
%A Jauhiainen, Tommi
%A Jauhiainen, Heidi
%A Lindén, Krister
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%S Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kiyv, Ukraine
%F jauhiainen-etal-2021-naive
%X This article describes the experiments and systems developed by the SUKI team for the second edition of the Romanian Dialect Identification (RDI) shared task which was organized as part of the 2021 VarDial Evaluation Campaign. We submitted two runs to the shared task and our second submission was the overall best submission by a noticeable margin. Our best submission used a character n-gram based naive Bayes classifier with adaptive language models. We describe our experiments on the development set leading to both submissions.
%U https://aclanthology.org/2021.vardial-1.9
%P 76-83
Markdown (Informal)
[Naive Bayes-based Experiments in Romanian Dialect Identification](https://aclanthology.org/2021.vardial-1.9) (Jauhiainen et al., VarDial 2021)
ACL