@inproceedings{gavriilidou-sidiropoulos-2026-hellenic,
title = "{H}ellenic National Corpus: The Current State",
author = "Gavriilidou, Maria and
Sidiropoulos, Nikolaos",
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-1.7/",
doi = "10.63317/492hm739pspc",
pages = "57--62",
abstract = "The Hellenic National Corpus (HNC) is an integrated online environment offering access to standard Modern Greek language material and to related analysis tools. The HNC corpus has been developed in two main phases, and currently comprises over 97 million words exclusively of written language, sourced from printed resources or scraped from the internet. The material has been automatically lemmatized and morphologically annotated, while a subset of 100,000 words has been further manually corrected, in order to produce a freely downloadable error-free corpus. Through the dedicated platform, the users have access to concordances, morphological analysis of words and statistical information (frequency) at word, lemma, part of speech and n-gram levels. Future steps include the expansion of the material in both historical and coverage dimensions: the inclusion of material from older phases of the language is foreseen, as well as the addition of dialectal material besides standards language."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gavriilidou-sidiropoulos-2026-hellenic">
<titleInfo>
<title>Hellenic National Corpus: The Current State</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Gavriilidou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Sidiropoulos</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 Hellenic National Corpus (HNC) is an integrated online environment offering access to standard Modern Greek language material and to related analysis tools. The HNC corpus has been developed in two main phases, and currently comprises over 97 million words exclusively of written language, sourced from printed resources or scraped from the internet. The material has been automatically lemmatized and morphologically annotated, while a subset of 100,000 words has been further manually corrected, in order to produce a freely downloadable error-free corpus. Through the dedicated platform, the users have access to concordances, morphological analysis of words and statistical information (frequency) at word, lemma, part of speech and n-gram levels. Future steps include the expansion of the material in both historical and coverage dimensions: the inclusion of material from older phases of the language is foreseen, as well as the addition of dialectal material besides standards language.</abstract>
<identifier type="citekey">gavriilidou-sidiropoulos-2026-hellenic</identifier>
<identifier type="doi">10.63317/492hm739pspc</identifier>
<location>
<url>https://aclanthology.org/2026.cmlc-1.7/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>57</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hellenic National Corpus: The Current State
%A Gavriilidou, Maria
%A Sidiropoulos, Nikolaos
%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 gavriilidou-sidiropoulos-2026-hellenic
%X The Hellenic National Corpus (HNC) is an integrated online environment offering access to standard Modern Greek language material and to related analysis tools. The HNC corpus has been developed in two main phases, and currently comprises over 97 million words exclusively of written language, sourced from printed resources or scraped from the internet. The material has been automatically lemmatized and morphologically annotated, while a subset of 100,000 words has been further manually corrected, in order to produce a freely downloadable error-free corpus. Through the dedicated platform, the users have access to concordances, morphological analysis of words and statistical information (frequency) at word, lemma, part of speech and n-gram levels. Future steps include the expansion of the material in both historical and coverage dimensions: the inclusion of material from older phases of the language is foreseen, as well as the addition of dialectal material besides standards language.
%R 10.63317/492hm739pspc
%U https://aclanthology.org/2026.cmlc-1.7/
%U https://doi.org/10.63317/492hm739pspc
%P 57-62
Markdown (Informal)
[Hellenic National Corpus: The Current State](https://aclanthology.org/2026.cmlc-1.7/) (Gavriilidou & Sidiropoulos, CMLC 2026)
ACL
- Maria Gavriilidou and Nikolaos Sidiropoulos. 2026. Hellenic National Corpus: The Current State. In Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora, pages 57–62, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).