@inproceedings{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",
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-1.518/",
doi = "10.63317/59wsms6588ys",
pages = "6528--6535",
abstract = "This paper introduces DeLiKo-2025@DNB, a very large, linguistically annotated corpus of German-language contemporary literature, freely accessible via \url{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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kupietz-etal-2026-national">
<titleInfo>
<title>National Library as Corpus: DeLiKo-2025@DNB – a Very Large Corpus of German-language Contemporary Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Kupietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Diewald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Genêt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Witt</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>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.</abstract>
<identifier type="citekey">kupietz-etal-2026-national</identifier>
<identifier type="doi">10.63317/59wsms6588ys</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.518/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6528</start>
<end>6535</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T National Library as Corpus: DeLiKo-2025@DNB – a Very Large Corpus of German-language Contemporary Literature
%A Kupietz, Marc
%A Diewald, Nils
%A Genêt, Philippe
%A Witt, Andreas
%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 kupietz-etal-2026-national
%X 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.
%R 10.63317/59wsms6588ys
%U https://aclanthology.org/2026.lrec-1.518/
%U https://doi.org/10.63317/59wsms6588ys
%P 6528-6535
Markdown (Informal)
[National Library as Corpus: DeLiKo-2025@DNB – a Very Large Corpus of German-language Contemporary Literature](https://aclanthology.org/2026.lrec-1.518/) (Kupietz et al., LREC 2026)
ACL