@article{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",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.287/",
    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."
}