@inproceedings{steingrimsson-etal-2025-mc,
title = "{MC-19:} A Corpus of 19th Century {Icelandic} Texts",
author = "Steingr{\'i}msson, Stein{\th}{\'o}r and
Sigur{\dh}sson, Einar Freyr and
Jasonarson, Atli",
editor = "Johansson, Richard and
Stymne, Sara",
booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2025.nodalida-1.68/",
pages = "680--687",
ISBN = "978-9908-53-109-0",
abstract = "We present MC-19, a new Icelandic historical corpus containing texts from the period 1800-1920. We describe approaches for enhancing a corpus of historical texts, by preparing the texts so that they can be processed using state-of-the-art NLP tools. We train encoder-decoder models to reduce the number of OCR errors while leaving other orthographical variation be. We generate a separate modern spelling layer by normalizing the spelling to comply with modern spelling rules, using a statistical modernization ruleset as well as a dictionary of the most common words. This allows for the texts to be PoS-tagged and lemmatized using available tools, facilitating usage of the corpus for researchers and language technologists. The published version of the corpus contains over 270 million tokens."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="steingrimsson-etal-2025-mc">
<titleInfo>
<title>MC-19: A Corpus of 19th Century Icelandic Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stein\thór</namePart>
<namePart type="family">Steingrímsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Einar</namePart>
<namePart type="given">Freyr</namePart>
<namePart type="family">Sigur\dhsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atli</namePart>
<namePart type="family">Jasonarson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Johansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-109-0</identifier>
</relatedItem>
<abstract>We present MC-19, a new Icelandic historical corpus containing texts from the period 1800-1920. We describe approaches for enhancing a corpus of historical texts, by preparing the texts so that they can be processed using state-of-the-art NLP tools. We train encoder-decoder models to reduce the number of OCR errors while leaving other orthographical variation be. We generate a separate modern spelling layer by normalizing the spelling to comply with modern spelling rules, using a statistical modernization ruleset as well as a dictionary of the most common words. This allows for the texts to be PoS-tagged and lemmatized using available tools, facilitating usage of the corpus for researchers and language technologists. The published version of the corpus contains over 270 million tokens.</abstract>
<identifier type="citekey">steingrimsson-etal-2025-mc</identifier>
<location>
<url>https://aclanthology.org/2025.nodalida-1.68/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>680</start>
<end>687</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MC-19: A Corpus of 19th Century Icelandic Texts
%A Steingrímsson, Stein\thór
%A Sigur\dhsson, Einar Freyr
%A Jasonarson, Atli
%Y Johansson, Richard
%Y Stymne, Sara
%S Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)
%D 2025
%8 March
%I University of Tartu Library
%C Tallinn, Estonia
%@ 978-9908-53-109-0
%F steingrimsson-etal-2025-mc
%X We present MC-19, a new Icelandic historical corpus containing texts from the period 1800-1920. We describe approaches for enhancing a corpus of historical texts, by preparing the texts so that they can be processed using state-of-the-art NLP tools. We train encoder-decoder models to reduce the number of OCR errors while leaving other orthographical variation be. We generate a separate modern spelling layer by normalizing the spelling to comply with modern spelling rules, using a statistical modernization ruleset as well as a dictionary of the most common words. This allows for the texts to be PoS-tagged and lemmatized using available tools, facilitating usage of the corpus for researchers and language technologists. The published version of the corpus contains over 270 million tokens.
%U https://aclanthology.org/2025.nodalida-1.68/
%P 680-687
Markdown (Informal)
[MC-19: A Corpus of 19th Century Icelandic Texts](https://aclanthology.org/2025.nodalida-1.68/) (Steingrímsson et al., NoDaLiDa 2025)
ACL
- Steinþór Steingrímsson, Einar Freyr Sigurðsson, and Atli Jasonarson. 2025. MC-19: A Corpus of 19th Century Icelandic Texts. In Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 680–687, Tallinn, Estonia. University of Tartu Library.