@inproceedings{vakili-etal-2025-sweclineval,
title = "{SweClinEval}: {A} Benchmark for {Swedish} Clinical Natural Language Processing",
author = "Vakili, Thomas and
Hansson, Martin and
Henriksson, Aron",
editor = "Johansson, Richard and
Stymne, Sara",
booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2025.nodalida-1.76/",
pages = "767--775",
ISBN = "978-9908-53-109-0",
abstract = "The lack of benchmarks in certain domains and for certain languages makes it difficult to track progress regarding the state-of-the-art of NLP in those areas, potentially impeding progress in important, specialized domains. Here, we introduce the first Swedish benchmark for clinical NLP: {\_}SweClinEval{\_}. The first iteration of the benchmark consists of six clinical NLP tasks, encompassing both document-level classification and named entity recognition tasks, with real clinical data. We evaluate nine different encoder models, both Swedish and multilingual. The results show that domain-adapted models outperform generic models on sequence-level classification tasks, while certain larger generic models outperform the clinical models on named entity recognition tasks. We describe how the benchmark can be managed despite limited possibilities to share sensitive clinical data, and discuss plans for extending the benchmark in future iterations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vakili-etal-2025-sweclineval">
<titleInfo>
<title>SweClinEval: A Benchmark for Swedish Clinical Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Vakili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Hansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aron</namePart>
<namePart type="family">Henriksson</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 Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Johansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-109-0</identifier>
</relatedItem>
<abstract>The lack of benchmarks in certain domains and for certain languages makes it difficult to track progress regarding the state-of-the-art of NLP in those areas, potentially impeding progress in important, specialized domains. Here, we introduce the first Swedish benchmark for clinical NLP: _SweClinEval_. The first iteration of the benchmark consists of six clinical NLP tasks, encompassing both document-level classification and named entity recognition tasks, with real clinical data. We evaluate nine different encoder models, both Swedish and multilingual. The results show that domain-adapted models outperform generic models on sequence-level classification tasks, while certain larger generic models outperform the clinical models on named entity recognition tasks. We describe how the benchmark can be managed despite limited possibilities to share sensitive clinical data, and discuss plans for extending the benchmark in future iterations.</abstract>
<identifier type="citekey">vakili-etal-2025-sweclineval</identifier>
<location>
<url>https://aclanthology.org/2025.nodalida-1.76/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>767</start>
<end>775</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SweClinEval: A Benchmark for Swedish Clinical Natural Language Processing
%A Vakili, Thomas
%A Hansson, Martin
%A Henriksson, Aron
%Y Johansson, Richard
%Y Stymne, Sara
%S Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)
%D 2025
%8 March
%I University of Tartu Library
%C Tallinn, Estonia
%@ 978-9908-53-109-0
%F vakili-etal-2025-sweclineval
%X The lack of benchmarks in certain domains and for certain languages makes it difficult to track progress regarding the state-of-the-art of NLP in those areas, potentially impeding progress in important, specialized domains. Here, we introduce the first Swedish benchmark for clinical NLP: _SweClinEval_. The first iteration of the benchmark consists of six clinical NLP tasks, encompassing both document-level classification and named entity recognition tasks, with real clinical data. We evaluate nine different encoder models, both Swedish and multilingual. The results show that domain-adapted models outperform generic models on sequence-level classification tasks, while certain larger generic models outperform the clinical models on named entity recognition tasks. We describe how the benchmark can be managed despite limited possibilities to share sensitive clinical data, and discuss plans for extending the benchmark in future iterations.
%U https://aclanthology.org/2025.nodalida-1.76/
%P 767-775
Markdown (Informal)
[SweClinEval: A Benchmark for Swedish Clinical Natural Language Processing](https://aclanthology.org/2025.nodalida-1.76/) (Vakili et al., NoDaLiDa 2025)
ACL