@inproceedings{kummervold-etal-2022-norwegian,
title = "The {N}orwegian Colossal Corpus: A Text Corpus for Training Large {N}orwegian Language Models",
author = "Kummervold, Per and
Wetjen, Freddy and
de la Rosa, Javier",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.410",
pages = "3852--3860",
abstract = "Norwegian has been one of many languages lacking sufficient available text to train quality language models. In an attempt to bridge this gap, we introduce the Norwegian Colossal Corpus (NCC), which comprises 49GB of clean Norwegian textual data containing over 7B words. The NCC is composed of different and varied sources, ranging from books and newspapers to government documents and public reports, showcasing the various uses of the Norwegian language in society. The corpus contains mainly Norwegian Bokm{\aa}l and Norwegian Nynorsk. Each document in the corpus is tagged with metadata that enables the creation of sub-corpora for specific needs. Its structure makes it easy to combine with large web archives that for licensing reasons could not be distributed together with the NCC. By releasing this corpus openly to the public, we hope to foster the creation of both better Norwegian language models and multilingual language models with support for Norwegian.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kummervold-etal-2022-norwegian">
<titleInfo>
<title>The Norwegian Colossal Corpus: A Text Corpus for Training Large Norwegian Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Per</namePart>
<namePart type="family">Kummervold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Freddy</namePart>
<namePart type="family">Wetjen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">de la Rosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Norwegian has been one of many languages lacking sufficient available text to train quality language models. In an attempt to bridge this gap, we introduce the Norwegian Colossal Corpus (NCC), which comprises 49GB of clean Norwegian textual data containing over 7B words. The NCC is composed of different and varied sources, ranging from books and newspapers to government documents and public reports, showcasing the various uses of the Norwegian language in society. The corpus contains mainly Norwegian Bokmål and Norwegian Nynorsk. Each document in the corpus is tagged with metadata that enables the creation of sub-corpora for specific needs. Its structure makes it easy to combine with large web archives that for licensing reasons could not be distributed together with the NCC. By releasing this corpus openly to the public, we hope to foster the creation of both better Norwegian language models and multilingual language models with support for Norwegian.</abstract>
<identifier type="citekey">kummervold-etal-2022-norwegian</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.410</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3852</start>
<end>3860</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Norwegian Colossal Corpus: A Text Corpus for Training Large Norwegian Language Models
%A Kummervold, Per
%A Wetjen, Freddy
%A de la Rosa, Javier
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F kummervold-etal-2022-norwegian
%X Norwegian has been one of many languages lacking sufficient available text to train quality language models. In an attempt to bridge this gap, we introduce the Norwegian Colossal Corpus (NCC), which comprises 49GB of clean Norwegian textual data containing over 7B words. The NCC is composed of different and varied sources, ranging from books and newspapers to government documents and public reports, showcasing the various uses of the Norwegian language in society. The corpus contains mainly Norwegian Bokmål and Norwegian Nynorsk. Each document in the corpus is tagged with metadata that enables the creation of sub-corpora for specific needs. Its structure makes it easy to combine with large web archives that for licensing reasons could not be distributed together with the NCC. By releasing this corpus openly to the public, we hope to foster the creation of both better Norwegian language models and multilingual language models with support for Norwegian.
%U https://aclanthology.org/2022.lrec-1.410
%P 3852-3860
Markdown (Informal)
[The Norwegian Colossal Corpus: A Text Corpus for Training Large Norwegian Language Models](https://aclanthology.org/2022.lrec-1.410) (Kummervold et al., LREC 2022)
ACL