@inproceedings{fedorova-etal-2025-multi,
title = "Multi-label {S}candinavian Language Identification ({SLIDE})",
author = "Fedorova, Mariia and
Frydenberg, Jonas Sebulon and
Handford, Victoria and
Lang{\o}, Victoria Ovedie Chruickshank and
Willoch, Solveig Helene and
Midtgaard, Marthe L{\o}ken and
Scherrer, Yves and
M{\ae}hlum, Petter and
Samuel, David",
editor = "Holdt, {\v{S}}pela Arhar and
Ilinykh, Nikolai and
Scalvini, Barbara and
Bruton, Micaella and
Debess, Iben Nyholm and
Tudor, Crina Madalina",
booktitle = "Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library, Estonia",
url = "https://aclanthology.org/2025.resourceful-1.33/",
pages = "179--189",
ISBN = "978-9908-53-121-2",
abstract = "Identifying closely related languages at sentence level is difficult, in particular because it is often impossible to assign a sentence to a single language. In this paper, we focus on multi-label sentence-level Scandinavian language identification (LID) for Danish, Norwegian Bokm{\r{a}}l, Norwegian Nynorsk, and Swedish. We present the Scandinavian Language Identification and Evaluation, SLIDE, a manually curated multi-label evaluation dataset and a suite of LID models with varying speed{--}accuracy tradeoffs. We demonstrate that the ability to identify multiple languages simultaneously is necessary for any accurate LID method, and present a novel approach to training such multi-label LID models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fedorova-etal-2025-multi">
<titleInfo>
<title>Multi-label Scandinavian Language Identification (SLIDE)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariia</namePart>
<namePart type="family">Fedorova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="given">Sebulon</namePart>
<namePart type="family">Frydenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Handford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="given">Ovedie</namePart>
<namePart type="given">Chruickshank</namePart>
<namePart type="family">Langø</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Solveig</namePart>
<namePart type="given">Helene</namePart>
<namePart type="family">Willoch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marthe</namePart>
<namePart type="given">Løken</namePart>
<namePart type="family">Midtgaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</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">David</namePart>
<namePart type="family">Samuel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Špela</namePart>
<namePart type="given">Arhar</namePart>
<namePart type="family">Holdt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Micaella</namePart>
<namePart type="family">Bruton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iben</namePart>
<namePart type="given">Nyholm</namePart>
<namePart type="family">Debess</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Crina</namePart>
<namePart type="given">Madalina</namePart>
<namePart type="family">Tudor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library, Estonia</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-121-2</identifier>
</relatedItem>
<abstract>Identifying closely related languages at sentence level is difficult, in particular because it is often impossible to assign a sentence to a single language. In this paper, we focus on multi-label sentence-level Scandinavian language identification (LID) for Danish, Norwegian Bokmål, Norwegian Nynorsk, and Swedish. We present the Scandinavian Language Identification and Evaluation, SLIDE, a manually curated multi-label evaluation dataset and a suite of LID models with varying speed–accuracy tradeoffs. We demonstrate that the ability to identify multiple languages simultaneously is necessary for any accurate LID method, and present a novel approach to training such multi-label LID models.</abstract>
<identifier type="citekey">fedorova-etal-2025-multi</identifier>
<location>
<url>https://aclanthology.org/2025.resourceful-1.33/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>179</start>
<end>189</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-label Scandinavian Language Identification (SLIDE)
%A Fedorova, Mariia
%A Frydenberg, Jonas Sebulon
%A Handford, Victoria
%A Langø, Victoria Ovedie Chruickshank
%A Willoch, Solveig Helene
%A Midtgaard, Marthe Løken
%A Scherrer, Yves
%A Mæhlum, Petter
%A Samuel, David
%Y Holdt, Špela Arhar
%Y Ilinykh, Nikolai
%Y Scalvini, Barbara
%Y Bruton, Micaella
%Y Debess, Iben Nyholm
%Y Tudor, Crina Madalina
%S Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)
%D 2025
%8 March
%I University of Tartu Library, Estonia
%C Tallinn, Estonia
%@ 978-9908-53-121-2
%F fedorova-etal-2025-multi
%X Identifying closely related languages at sentence level is difficult, in particular because it is often impossible to assign a sentence to a single language. In this paper, we focus on multi-label sentence-level Scandinavian language identification (LID) for Danish, Norwegian Bokmål, Norwegian Nynorsk, and Swedish. We present the Scandinavian Language Identification and Evaluation, SLIDE, a manually curated multi-label evaluation dataset and a suite of LID models with varying speed–accuracy tradeoffs. We demonstrate that the ability to identify multiple languages simultaneously is necessary for any accurate LID method, and present a novel approach to training such multi-label LID models.
%U https://aclanthology.org/2025.resourceful-1.33/
%P 179-189
Markdown (Informal)
[Multi-label Scandinavian Language Identification (SLIDE)](https://aclanthology.org/2025.resourceful-1.33/) (Fedorova et al., RESOURCEFUL 2025)
ACL
- Mariia Fedorova, Jonas Sebulon Frydenberg, Victoria Handford, Victoria Ovedie Chruickshank Langø, Solveig Helene Willoch, Marthe Løken Midtgaard, Yves Scherrer, Petter Mæhlum, and David Samuel. 2025. Multi-label Scandinavian Language Identification (SLIDE). In Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025), pages 179–189, Tallinn, Estonia. University of Tartu Library, Estonia.