@inproceedings{jauhiainen-etal-2020-uralic,
title = "{U}ralic Language Identification ({ULI}) 2020 shared task dataset and the Wanca 2017 corpora",
author = "Jauhiainen, Tommi and
Jauhiainen, Heidi and
Partanen, Niko 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},
booktitle = "Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics (ICCL)",
url = "https://aclanthology.org/2020.vardial-1.16",
pages = "173--185",
abstract = "This article introduces the Wanca 2017 web corpora from which the sentences written in minor Uralic languages were collected for the test set of the Uralic Language Identification (ULI) 2020 shared task. We describe the ULI shared task and how the test set was constructed using the Wanca 2017 corpora and texts in different languages from the Leipzig corpora collection. We also provide the results of a baseline language identification experiment conducted using the ULI 2020 dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jauhiainen-etal-2020-uralic">
<titleInfo>
<title>Uralic Language Identification (ULI) 2020 shared task dataset and the Wanca 2017 corpora</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">Niko</namePart>
<namePart type="family">Partanen</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>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th 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>
<originInfo>
<publisher>International Committee on Computational Linguistics (ICCL)</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article introduces the Wanca 2017 web corpora from which the sentences written in minor Uralic languages were collected for the test set of the Uralic Language Identification (ULI) 2020 shared task. We describe the ULI shared task and how the test set was constructed using the Wanca 2017 corpora and texts in different languages from the Leipzig corpora collection. We also provide the results of a baseline language identification experiment conducted using the ULI 2020 dataset.</abstract>
<identifier type="citekey">jauhiainen-etal-2020-uralic</identifier>
<location>
<url>https://aclanthology.org/2020.vardial-1.16</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>173</start>
<end>185</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uralic Language Identification (ULI) 2020 shared task dataset and the Wanca 2017 corpora
%A Jauhiainen, Tommi
%A Jauhiainen, Heidi
%A Partanen, Niko
%A Lindén, Krister
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Scherrer, Yves
%S Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2020
%8 December
%I International Committee on Computational Linguistics (ICCL)
%C Barcelona, Spain (Online)
%F jauhiainen-etal-2020-uralic
%X This article introduces the Wanca 2017 web corpora from which the sentences written in minor Uralic languages were collected for the test set of the Uralic Language Identification (ULI) 2020 shared task. We describe the ULI shared task and how the test set was constructed using the Wanca 2017 corpora and texts in different languages from the Leipzig corpora collection. We also provide the results of a baseline language identification experiment conducted using the ULI 2020 dataset.
%U https://aclanthology.org/2020.vardial-1.16
%P 173-185
Markdown (Informal)
[Uralic Language Identification (ULI) 2020 shared task dataset and the Wanca 2017 corpora](https://aclanthology.org/2020.vardial-1.16) (Jauhiainen et al., VarDial 2020)
ACL