@article{kupietz-etal-2026-national,
    title = "National Library as Corpus: {D}e{L}i{K}o-2025@{DNB} {--} a Very Large Corpus of {G}erman-language Contemporary Literature",
    author = "Kupietz, Marc  and
      Diewald, Nils  and
      Gen{\^e}t, Philippe  and
      Witt, Andreas",
    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.518/",
    pages = "6528--6535",
    abstract = "This paper introduces DeLiKo-2025@DNB, a very large, linguistically annotated corpus of German-language contemporary literature, freely accessible via https://korap.dnb.de/. The corpus currently comprises 21 billion words from over 287,000 books published between 2005 and the present, spanning pulp and genre fiction as well as literary award-winning works. It covers the entire holdings of EPUB-format fiction ebooks deposited with the German National Library (DNB). We provide a detailed account of the corpus composition, metadata, and key features. Additionally, we explain our strategy for enabling lawful and effective access through the deployment of the open-source corpus analysis platform KorAP at the DNB, and we discuss both the transferability of our approach and work to other national libraries and our ongoing and planned extensions and enhancements."
}