@inproceedings{ogrodniczuk-etal-2026-polish,
title = "The {P}olish {P}ress{M}int Corpus",
author = "Ogrodniczuk, Maciej and
Czerski, Dariusz and
Paw{\l}owski, Adam",
editor = "Ogrodniczuk, Maciej and
Osenova, Petya and
Wissik, Tanja",
booktitle = "Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.pressmint-1.2/",
doi = "10.63317/3rqajugehtb3",
pages = "6--10",
abstract = "This article presents the Polish contribution to the PressMint project, a CLARIN initiative aimed at creating a pan-European, multilingual corpus of historical newspapers. The Polish dataset consists of three subcorpora spanning 110 years (1830{--}1939). The first two components are drawn from the Microcorpus of Nineteenth-Century Polish (its short press texts and journalistic texts subcorpora), each containing 200 samples of brief news items and journalistic articles from diverse periodicals. The third component, the InterWar Corpus, covers the period 1918{--}1939 and comprises approximately 6.5 million words from complete newspaper issues, representing the territory of the interwar Republic of Poland. The authors argue for the scholarly value of historical press, highlighting its precise chronological dating as a key advantage for diachronic research despite challenges such as heterogeneous content and anonymous authorship. The conversion pipeline maps source metadata to a standardized TEI format and enriches texts with linguistic annotation using the Hydra NLP tool, providing lemmatization, part-of-speech tagging (mapped to Universal Dependencies), dependency parsing, and named entity recognition. The resulting openly accessible dataset enables cross-linguistic comparison and distant reading of historical press materials on a European scale."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ogrodniczuk-etal-2026-polish">
<titleInfo>
<title>The Polish PressMint Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dariusz</namePart>
<namePart type="family">Czerski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Pawłowski</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 First Workshop on Creating Interoperable Corpora of Historical Newspapers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Wissik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article presents the Polish contribution to the PressMint project, a CLARIN initiative aimed at creating a pan-European, multilingual corpus of historical newspapers. The Polish dataset consists of three subcorpora spanning 110 years (1830–1939). The first two components are drawn from the Microcorpus of Nineteenth-Century Polish (its short press texts and journalistic texts subcorpora), each containing 200 samples of brief news items and journalistic articles from diverse periodicals. The third component, the InterWar Corpus, covers the period 1918–1939 and comprises approximately 6.5 million words from complete newspaper issues, representing the territory of the interwar Republic of Poland. The authors argue for the scholarly value of historical press, highlighting its precise chronological dating as a key advantage for diachronic research despite challenges such as heterogeneous content and anonymous authorship. The conversion pipeline maps source metadata to a standardized TEI format and enriches texts with linguistic annotation using the Hydra NLP tool, providing lemmatization, part-of-speech tagging (mapped to Universal Dependencies), dependency parsing, and named entity recognition. The resulting openly accessible dataset enables cross-linguistic comparison and distant reading of historical press materials on a European scale.</abstract>
<identifier type="citekey">ogrodniczuk-etal-2026-polish</identifier>
<identifier type="doi">10.63317/3rqajugehtb3</identifier>
<location>
<url>https://aclanthology.org/2026.pressmint-1.2/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Polish PressMint Corpus
%A Ogrodniczuk, Maciej
%A Czerski, Dariusz
%A Pawłowski, Adam
%Y Ogrodniczuk, Maciej
%Y Osenova, Petya
%Y Wissik, Tanja
%S Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma de Mallorca, Spain
%F ogrodniczuk-etal-2026-polish
%X This article presents the Polish contribution to the PressMint project, a CLARIN initiative aimed at creating a pan-European, multilingual corpus of historical newspapers. The Polish dataset consists of three subcorpora spanning 110 years (1830–1939). The first two components are drawn from the Microcorpus of Nineteenth-Century Polish (its short press texts and journalistic texts subcorpora), each containing 200 samples of brief news items and journalistic articles from diverse periodicals. The third component, the InterWar Corpus, covers the period 1918–1939 and comprises approximately 6.5 million words from complete newspaper issues, representing the territory of the interwar Republic of Poland. The authors argue for the scholarly value of historical press, highlighting its precise chronological dating as a key advantage for diachronic research despite challenges such as heterogeneous content and anonymous authorship. The conversion pipeline maps source metadata to a standardized TEI format and enriches texts with linguistic annotation using the Hydra NLP tool, providing lemmatization, part-of-speech tagging (mapped to Universal Dependencies), dependency parsing, and named entity recognition. The resulting openly accessible dataset enables cross-linguistic comparison and distant reading of historical press materials on a European scale.
%R 10.63317/3rqajugehtb3
%U https://aclanthology.org/2026.pressmint-1.2/
%U https://doi.org/10.63317/3rqajugehtb3
%P 6-10
Markdown (Informal)
[The Polish PressMint Corpus](https://aclanthology.org/2026.pressmint-1.2/) (Ogrodniczuk et al., PressMint 2026)
ACL
- Maciej Ogrodniczuk, Dariusz Czerski, and Adam Pawłowski. 2026. The Polish PressMint Corpus. In Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers, pages 6–10, Palma de Mallorca, Spain. Association for Computational Linguistics.