@inproceedings{lassche-etal-2026-evaluating,
title = "Evaluating Embedding Models on {D}anish Historical Newspapers: A Corpus and Benchmark Resource",
author = "Lassche, Alie and
Feldkamp, Pascale and
Bizzoni, Yuri and
Baunvig, Katrine and
Nielbo, Kristoffer and
Heinsen, Johan",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.287/",
doi = "10.63317/2hzf85aou6dw",
pages = "3577--3589",
abstract = "We present an enriched dataset of almost five million Danish historical newspaper articles from the late seventeenth to nineteenth century, augmented with semantic embeddings and an annotated subset, to enable semi-automated classification as well as thematic and linguistic exploration. Through three historical benchmark tasks that evaluate the performance of Danish and multilingual embedding models on this historical Danish corpus, we discuss how the choice for an embedding model depends on the type of task, and enrich our corpus with embeddings from the overall best performing model. As a showcase experiment, we look at the distribution of article categories in the three subgenres that can be observed in the corpus. This experiment highlights the corpus and article-level embeddings' potential for further exploration and analysis of the Danish historical mediascape. The resource is freely available for research use and aims to foster reproducible, data-driven studies of language and culture in the Danish nineteenth century."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lassche-etal-2026-evaluating">
<titleInfo>
<title>Evaluating Embedding Models on Danish Historical Newspapers: A Corpus and Benchmark Resource</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alie</namePart>
<namePart type="family">Lassche</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Feldkamp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrine</namePart>
<namePart type="family">Baunvig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristoffer</namePart>
<namePart type="family">Nielbo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johan</namePart>
<namePart type="family">Heinsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present an enriched dataset of almost five million Danish historical newspaper articles from the late seventeenth to nineteenth century, augmented with semantic embeddings and an annotated subset, to enable semi-automated classification as well as thematic and linguistic exploration. Through three historical benchmark tasks that evaluate the performance of Danish and multilingual embedding models on this historical Danish corpus, we discuss how the choice for an embedding model depends on the type of task, and enrich our corpus with embeddings from the overall best performing model. As a showcase experiment, we look at the distribution of article categories in the three subgenres that can be observed in the corpus. This experiment highlights the corpus and article-level embeddings’ potential for further exploration and analysis of the Danish historical mediascape. The resource is freely available for research use and aims to foster reproducible, data-driven studies of language and culture in the Danish nineteenth century.</abstract>
<identifier type="citekey">lassche-etal-2026-evaluating</identifier>
<identifier type="doi">10.63317/2hzf85aou6dw</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.287/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3577</start>
<end>3589</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Embedding Models on Danish Historical Newspapers: A Corpus and Benchmark Resource
%A Lassche, Alie
%A Feldkamp, Pascale
%A Bizzoni, Yuri
%A Baunvig, Katrine
%A Nielbo, Kristoffer
%A Heinsen, Johan
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F lassche-etal-2026-evaluating
%X We present an enriched dataset of almost five million Danish historical newspaper articles from the late seventeenth to nineteenth century, augmented with semantic embeddings and an annotated subset, to enable semi-automated classification as well as thematic and linguistic exploration. Through three historical benchmark tasks that evaluate the performance of Danish and multilingual embedding models on this historical Danish corpus, we discuss how the choice for an embedding model depends on the type of task, and enrich our corpus with embeddings from the overall best performing model. As a showcase experiment, we look at the distribution of article categories in the three subgenres that can be observed in the corpus. This experiment highlights the corpus and article-level embeddings’ potential for further exploration and analysis of the Danish historical mediascape. The resource is freely available for research use and aims to foster reproducible, data-driven studies of language and culture in the Danish nineteenth century.
%R 10.63317/2hzf85aou6dw
%U https://aclanthology.org/2026.lrec-1.287/
%U https://doi.org/10.63317/2hzf85aou6dw
%P 3577-3589
Markdown (Informal)
[Evaluating Embedding Models on Danish Historical Newspapers: A Corpus and Benchmark Resource](https://aclanthology.org/2026.lrec-1.287/) (Lassche et al., LREC 2026)
ACL