@inproceedings{shim-nerbonne-2022-dialectr,
title = "dialect{R}: Doing Dialectometry in {R}",
author = "Shim, Ryan Soh-Eun and
Nerbonne, John",
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-1.3",
pages = "20--27",
abstract = "We present dialectR, an open-source R package for performing quantitative analyses of dialects based on categorical measures of difference and on variants of edit distance. dialectR stands as one of the first programmable toolkits that may freely be combined and extended by users with further statistical procedures. We describe implementational details of the package, and provide two examples of its use: one performing analyses based on multidimensional scaling and hierarchical clustering on a dataset of Dutch dialects, and another showing how an approximation of the acoustic vowel space may be achieved by performing an MFCC (Mel-Frequency Cepstral Coefficients)-based acoustic distance on audio recordings of vowels.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shim-nerbonne-2022-dialectr">
<titleInfo>
<title>dialectR: Doing Dialectometry in R</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="given">Soh-Eun</namePart>
<namePart type="family">Shim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Nerbonne</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>We present dialectR, an open-source R package for performing quantitative analyses of dialects based on categorical measures of difference and on variants of edit distance. dialectR stands as one of the first programmable toolkits that may freely be combined and extended by users with further statistical procedures. We describe implementational details of the package, and provide two examples of its use: one performing analyses based on multidimensional scaling and hierarchical clustering on a dataset of Dutch dialects, and another showing how an approximation of the acoustic vowel space may be achieved by performing an MFCC (Mel-Frequency Cepstral Coefficients)-based acoustic distance on audio recordings of vowels.</abstract>
<identifier type="citekey">shim-nerbonne-2022-dialectr</identifier>
<location>
<url>https://aclanthology.org/2022.vardial-1.3</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>20</start>
<end>27</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T dialectR: Doing Dialectometry in R
%A Shim, Ryan Soh-Eun
%A Nerbonne, John
%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 shim-nerbonne-2022-dialectr
%X We present dialectR, an open-source R package for performing quantitative analyses of dialects based on categorical measures of difference and on variants of edit distance. dialectR stands as one of the first programmable toolkits that may freely be combined and extended by users with further statistical procedures. We describe implementational details of the package, and provide two examples of its use: one performing analyses based on multidimensional scaling and hierarchical clustering on a dataset of Dutch dialects, and another showing how an approximation of the acoustic vowel space may be achieved by performing an MFCC (Mel-Frequency Cepstral Coefficients)-based acoustic distance on audio recordings of vowels.
%U https://aclanthology.org/2022.vardial-1.3
%P 20-27
Markdown (Informal)
[dialectR: Doing Dialectometry in R](https://aclanthology.org/2022.vardial-1.3) (Shim & Nerbonne, VarDial 2022)
ACL
- Ryan Soh-Eun Shim and John Nerbonne. 2022. dialectR: Doing Dialectometry in R. In Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects, pages 20–27, Gyeongju, Republic of Korea. Association for Computational Linguistics.