@inproceedings{barnes-etal-2021-nordial,
title = "{N}or{D}ial: A Preliminary Corpus of Written {N}orwegian Dialect Use",
author = "Barnes, Jeremy and
M{\ae}hlum, Petter and
Touileb, Samia",
editor = "Dobnik, Simon and
{\O}vrelid, Lilja",
booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may # " 31--2 " # jun,
year = "2021",
address = "Reykjavik, Iceland (Online)",
publisher = {Link{\"o}ping University Electronic Press, Sweden},
url = "https://aclanthology.org/2021.nodalida-main.51",
pages = "445--451",
abstract = "Norway has a large amount of dialectal variation, as well as a general tolerance to its use in the public sphere. There are, however, few available resources to study this variation and its change over time and in more informal areas, on social media. In this paper, we propose a first step to creating a corpus of dialectal variation of written Norwegian. We collect a small corpus of tweets and manually annotate them as Bokm{\aa}l, Nynorsk, any dialect, or a mix. We further perform preliminary experiments with state-of-the-art models, as well as an analysis of the data to expand this corpus in the future. Finally, we make the annotations available for future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barnes-etal-2021-nordial">
<titleInfo>
<title>NorDial: A Preliminary Corpus of Written Norwegian Dialect Use</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petter</namePart>
<namePart type="family">Mæhlum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-may 31–2 jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press, Sweden</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Norway has a large amount of dialectal variation, as well as a general tolerance to its use in the public sphere. There are, however, few available resources to study this variation and its change over time and in more informal areas, on social media. In this paper, we propose a first step to creating a corpus of dialectal variation of written Norwegian. We collect a small corpus of tweets and manually annotate them as Bokmål, Nynorsk, any dialect, or a mix. We further perform preliminary experiments with state-of-the-art models, as well as an analysis of the data to expand this corpus in the future. Finally, we make the annotations available for future work.</abstract>
<identifier type="citekey">barnes-etal-2021-nordial</identifier>
<location>
<url>https://aclanthology.org/2021.nodalida-main.51</url>
</location>
<part>
<date>2021-may 31–2 jun</date>
<extent unit="page">
<start>445</start>
<end>451</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NorDial: A Preliminary Corpus of Written Norwegian Dialect Use
%A Barnes, Jeremy
%A Mæhlum, Petter
%A Touileb, Samia
%Y Dobnik, Simon
%Y Øvrelid, Lilja
%S Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2021
%8 may 31–2 jun
%I Linköping University Electronic Press, Sweden
%C Reykjavik, Iceland (Online)
%F barnes-etal-2021-nordial
%X Norway has a large amount of dialectal variation, as well as a general tolerance to its use in the public sphere. There are, however, few available resources to study this variation and its change over time and in more informal areas, on social media. In this paper, we propose a first step to creating a corpus of dialectal variation of written Norwegian. We collect a small corpus of tweets and manually annotate them as Bokmål, Nynorsk, any dialect, or a mix. We further perform preliminary experiments with state-of-the-art models, as well as an analysis of the data to expand this corpus in the future. Finally, we make the annotations available for future work.
%U https://aclanthology.org/2021.nodalida-main.51
%P 445-451
Markdown (Informal)
[NorDial: A Preliminary Corpus of Written Norwegian Dialect Use](https://aclanthology.org/2021.nodalida-main.51) (Barnes et al., NoDaLiDa 2021)
ACL