@inproceedings{shvedova-lukashevskyi-2026-historical,
title = "Historical Newspapers in the General Regionally Annotated Corpus of {U}krainian ({GRAC}): Current State and {P}ress{M}int Integration Prospects",
author = "Shvedova, Maria and
Lukashevskyi, Arsenii",
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-1.5/",
doi = "10.63317/4zhmbuez4k25",
pages = "21--26",
abstract = "This paper presents the historical newspaper collection of the General Regionally Annotated Corpus of Ukrainian (GRAC) and outlines its prospective integration into the PressMint infrastructure. The collection comprises 117 newspaper titles published before 1950, totaling 23.6 million tokens, and reflects the political fragmentation, regional variation, and orthographic diversity of Ukrainian-language press from the late nineteenth to mid-twentieth century. We describe the corpus composition, temporal and geographic distribution, and metadata architecture. Special attention is given to morphosyntactic annotation challenges arising from the old Western Ukrainian orthography (Zhelekhivka), as well as issues related to annotating historical texts using the rule-based TagText parser and neural UDPipe2 models. The paper compares GRAC{'}s vertical format and metadata system with the TEI-based PressMint standard, identifying technical and conceptual harmonization challenges. Integrating GRAC newspapers into PressMint will facilitate comparative research on language policy, regional standardization, and media discourse within a broader European context."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shvedova-lukashevskyi-2026-historical">
<titleInfo>
<title>Historical Newspapers in the General Regionally Annotated Corpus of Ukrainian (GRAC): Current State and PressMint Integration Prospects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Shvedova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arsenii</namePart>
<namePart type="family">Lukashevskyi</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 paper presents the historical newspaper collection of the General Regionally Annotated Corpus of Ukrainian (GRAC) and outlines its prospective integration into the PressMint infrastructure. The collection comprises 117 newspaper titles published before 1950, totaling 23.6 million tokens, and reflects the political fragmentation, regional variation, and orthographic diversity of Ukrainian-language press from the late nineteenth to mid-twentieth century. We describe the corpus composition, temporal and geographic distribution, and metadata architecture. Special attention is given to morphosyntactic annotation challenges arising from the old Western Ukrainian orthography (Zhelekhivka), as well as issues related to annotating historical texts using the rule-based TagText parser and neural UDPipe2 models. The paper compares GRAC’s vertical format and metadata system with the TEI-based PressMint standard, identifying technical and conceptual harmonization challenges. Integrating GRAC newspapers into PressMint will facilitate comparative research on language policy, regional standardization, and media discourse within a broader European context.</abstract>
<identifier type="citekey">shvedova-lukashevskyi-2026-historical</identifier>
<identifier type="doi">10.63317/4zhmbuez4k25</identifier>
<location>
<url>https://aclanthology.org/2026.pressmint-1.5/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>21</start>
<end>26</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Historical Newspapers in the General Regionally Annotated Corpus of Ukrainian (GRAC): Current State and PressMint Integration Prospects
%A Shvedova, Maria
%A Lukashevskyi, Arsenii
%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 shvedova-lukashevskyi-2026-historical
%X This paper presents the historical newspaper collection of the General Regionally Annotated Corpus of Ukrainian (GRAC) and outlines its prospective integration into the PressMint infrastructure. The collection comprises 117 newspaper titles published before 1950, totaling 23.6 million tokens, and reflects the political fragmentation, regional variation, and orthographic diversity of Ukrainian-language press from the late nineteenth to mid-twentieth century. We describe the corpus composition, temporal and geographic distribution, and metadata architecture. Special attention is given to morphosyntactic annotation challenges arising from the old Western Ukrainian orthography (Zhelekhivka), as well as issues related to annotating historical texts using the rule-based TagText parser and neural UDPipe2 models. The paper compares GRAC’s vertical format and metadata system with the TEI-based PressMint standard, identifying technical and conceptual harmonization challenges. Integrating GRAC newspapers into PressMint will facilitate comparative research on language policy, regional standardization, and media discourse within a broader European context.
%R 10.63317/4zhmbuez4k25
%U https://aclanthology.org/2026.pressmint-1.5/
%U https://doi.org/10.63317/4zhmbuez4k25
%P 21-26
Markdown (Informal)
[Historical Newspapers in the General Regionally Annotated Corpus of Ukrainian (GRAC): Current State and PressMint Integration Prospects](https://aclanthology.org/2026.pressmint-1.5/) (Shvedova & Lukashevskyi, PressMint 2026)
ACL