@inproceedings{ligeti-nagy-etal-2026-managing,
title = "Managing Growth in a National Corpus: The {H}ungarian National Corpus 3.0 ({MNSZ}3)",
author = {Ligeti-Nagy, No{\'e}mi and
H{\'e}ja, Enik{\H{o}} and
B{\'a}nfi, {\'A}gnes and
F{\"o}ldesi, Fl{\'o}ra and
S{\'a}rossy, Bence and
Skrab{\'a}k, Bogl{\'a}rka and
V{\'a}radi, Tam{\'a}s and
Pr{\'o}sz{\'e}ky, G{\'a}bor},
editor = "Ba{\'n}ski, Piotr and
Knight, Dawn and
Kupietz, Marc and
Witt, Andreas and
Wr{\'o}blewska, Alina",
booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cmlc-1.14/",
doi = "10.63317/46aafswuwv4m",
pages = "84--90",
abstract = "The third generation of the Hungarian National Corpus (MNSZ3) aims to provide a large-scale, curated, and well-described corpus resource needed for the sustainable digital presence of Hungarian. Building on the domain structure and proportions of MNSZ2 (v2.0.5; 1.04 billion running words), the project targets a substantial increase in scale while also strengthening the coverage and metadata description of Hungarian language use outside Hungary. MNSZ3 retains the six traditional domains of the earlier corpus{---}press, fiction, scientific, official, personal, and transcribed spoken language{---}and is planned to reach approximately 10 billion tokens. This paper presents the motivation and design principles of the project, outlines the practical decisions and procedures used in data collection and cleaning, and discusses the annotation strategy developed for large-scale processing. In planning the linguistic analysis, we build on the complementary strengths of HuSpaCy and e-magyar: HuSpaCy provides the unified and efficient UD-oriented processing backbone, while e-magyar (emMorph) is preserved as an explicit additional layer for morphology and lemmatisation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ligeti-nagy-etal-2026-managing">
<titleInfo>
<title>Managing Growth in a National Corpus: The Hungarian National Corpus 3.0 (MNSZ3)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noémi</namePart>
<namePart type="family">Ligeti-Nagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enikő</namePart>
<namePart type="family">Héja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ágnes</namePart>
<namePart type="family">Bánfi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flóra</namePart>
<namePart type="family">Földesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bence</namePart>
<namePart type="family">Sárossy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boglárka</namePart>
<namePart type="family">Skrabák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamás</namePart>
<namePart type="family">Váradi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gábor</namePart>
<namePart type="family">Prószéky</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 12th Workshop on Challenges in the Management of Large Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Bański</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawn</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Kupietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Witt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Wróblewska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The third generation of the Hungarian National Corpus (MNSZ3) aims to provide a large-scale, curated, and well-described corpus resource needed for the sustainable digital presence of Hungarian. Building on the domain structure and proportions of MNSZ2 (v2.0.5; 1.04 billion running words), the project targets a substantial increase in scale while also strengthening the coverage and metadata description of Hungarian language use outside Hungary. MNSZ3 retains the six traditional domains of the earlier corpus—press, fiction, scientific, official, personal, and transcribed spoken language—and is planned to reach approximately 10 billion tokens. This paper presents the motivation and design principles of the project, outlines the practical decisions and procedures used in data collection and cleaning, and discusses the annotation strategy developed for large-scale processing. In planning the linguistic analysis, we build on the complementary strengths of HuSpaCy and e-magyar: HuSpaCy provides the unified and efficient UD-oriented processing backbone, while e-magyar (emMorph) is preserved as an explicit additional layer for morphology and lemmatisation.</abstract>
<identifier type="citekey">ligeti-nagy-etal-2026-managing</identifier>
<identifier type="doi">10.63317/46aafswuwv4m</identifier>
<location>
<url>https://aclanthology.org/2026.cmlc-1.14/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>84</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Managing Growth in a National Corpus: The Hungarian National Corpus 3.0 (MNSZ3)
%A Ligeti-Nagy, Noémi
%A Héja, Enikő
%A Bánfi, Ágnes
%A Földesi, Flóra
%A Sárossy, Bence
%A Skrabák, Boglárka
%A Váradi, Tamás
%A Prószéky, Gábor
%Y Bański, Piotr
%Y Knight, Dawn
%Y Kupietz, Marc
%Y Witt, Andreas
%Y Wróblewska, Alina
%S Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F ligeti-nagy-etal-2026-managing
%X The third generation of the Hungarian National Corpus (MNSZ3) aims to provide a large-scale, curated, and well-described corpus resource needed for the sustainable digital presence of Hungarian. Building on the domain structure and proportions of MNSZ2 (v2.0.5; 1.04 billion running words), the project targets a substantial increase in scale while also strengthening the coverage and metadata description of Hungarian language use outside Hungary. MNSZ3 retains the six traditional domains of the earlier corpus—press, fiction, scientific, official, personal, and transcribed spoken language—and is planned to reach approximately 10 billion tokens. This paper presents the motivation and design principles of the project, outlines the practical decisions and procedures used in data collection and cleaning, and discusses the annotation strategy developed for large-scale processing. In planning the linguistic analysis, we build on the complementary strengths of HuSpaCy and e-magyar: HuSpaCy provides the unified and efficient UD-oriented processing backbone, while e-magyar (emMorph) is preserved as an explicit additional layer for morphology and lemmatisation.
%R 10.63317/46aafswuwv4m
%U https://aclanthology.org/2026.cmlc-1.14/
%U https://doi.org/10.63317/46aafswuwv4m
%P 84-90
Markdown (Informal)
[Managing Growth in a National Corpus: The Hungarian National Corpus 3.0 (MNSZ3)](https://aclanthology.org/2026.cmlc-1.14/) (Ligeti-Nagy et al., CMLC 2026)
ACL
- Noémi Ligeti-Nagy, Enikő Héja, Ágnes Bánfi, Flóra Földesi, Bence Sárossy, Boglárka Skrabák, Tamás Váradi, and Gábor Prószéky. 2026. Managing Growth in a National Corpus: The Hungarian National Corpus 3.0 (MNSZ3). In Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora, pages 84–90, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).