@inproceedings{kuparinen-2023-murreviikko,
title = "Murreviikko - A Dialectologically Annotated and Normalized Dataset of {F}innish Tweets",
author = "Kuparinen, Olli",
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 = "Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.vardial-1.3/",
doi = "10.18653/v1/2023.vardial-1.3",
pages = "31--39",
abstract = "This paper presents Murreviikko, a dataset of dialectal Finnish tweets which have been dialectologically annotated and manually normalized to a standard form. The dataset can be used as a test set for dialect identification and dialect-to-standard normalization, for instance. We evaluate the dataset on the normalization task, comparing an existing normalization model built on a spoken dialect corpus and three newly trained models with different architectures. We find that there are significant differences in normalization difficulty between the dialects, and that a character-level statistical machine translation model performs best on the Murreviikko tweet dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kuparinen-2023-murreviikko">
<titleInfo>
<title>Murreviikko - A Dialectologically Annotated and Normalized Dataset of Finnish Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olli</namePart>
<namePart type="family">Kuparinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)</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">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents Murreviikko, a dataset of dialectal Finnish tweets which have been dialectologically annotated and manually normalized to a standard form. The dataset can be used as a test set for dialect identification and dialect-to-standard normalization, for instance. We evaluate the dataset on the normalization task, comparing an existing normalization model built on a spoken dialect corpus and three newly trained models with different architectures. We find that there are significant differences in normalization difficulty between the dialects, and that a character-level statistical machine translation model performs best on the Murreviikko tweet dataset.</abstract>
<identifier type="citekey">kuparinen-2023-murreviikko</identifier>
<identifier type="doi">10.18653/v1/2023.vardial-1.3</identifier>
<location>
<url>https://aclanthology.org/2023.vardial-1.3/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>31</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Murreviikko - A Dialectologically Annotated and Normalized Dataset of Finnish Tweets
%A Kuparinen, Olli
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%Y Ljubešić, Nikola
%Y Nakov, Preslav
%Y Tiedemann, Jörg
%Y Zampieri, Marcos
%S Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F kuparinen-2023-murreviikko
%X This paper presents Murreviikko, a dataset of dialectal Finnish tweets which have been dialectologically annotated and manually normalized to a standard form. The dataset can be used as a test set for dialect identification and dialect-to-standard normalization, for instance. We evaluate the dataset on the normalization task, comparing an existing normalization model built on a spoken dialect corpus and three newly trained models with different architectures. We find that there are significant differences in normalization difficulty between the dialects, and that a character-level statistical machine translation model performs best on the Murreviikko tweet dataset.
%R 10.18653/v1/2023.vardial-1.3
%U https://aclanthology.org/2023.vardial-1.3/
%U https://doi.org/10.18653/v1/2023.vardial-1.3
%P 31-39
Markdown (Informal)
[Murreviikko - A Dialectologically Annotated and Normalized Dataset of Finnish Tweets](https://aclanthology.org/2023.vardial-1.3/) (Kuparinen, VarDial 2023)
ACL