@inproceedings{kutuzov-etal-2021-large,
title = "Large-Scale Contextualised Language Modelling for {N}orwegian",
author = "Kutuzov, Andrey and
Barnes, Jeremy and
Velldal, Erik and
{\O}vrelid, Lilja and
Oepen, Stephan",
editor = "Dobnik, Simon and
{\O}vrelid, Lilja",
booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may # " 31--2 " # jun,
year = "2021",
address = "Reykjavik, Iceland (Online)",
publisher = {Link{\"o}ping University Electronic Press, Sweden},
url = "https://aclanthology.org/2021.nodalida-main.4/",
pages = "30--40",
abstract = "We present the ongoing NorLM initiative to support the creation and use of very large contextualised language models for Norwegian (and in principle other Nordic languages), including a ready-to-use software environment, as well as an experience report for data preparation and training. This paper introduces the first large-scale monolingual language models for Norwegian, based on both the ELMo and BERT frameworks. In addition to detailing the training process, we present contrastive benchmark results on a suite of NLP tasks for Norwegian. For additional background and access to the data, models, and software, please see: \url{http://norlm.nlpl.eu}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kutuzov-etal-2021-large">
<titleInfo>
<title>Large-Scale Contextualised Language Modelling for Norwegian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Kutuzov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Velldal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Oepen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-may 31–2 jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press, Sweden</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present the ongoing NorLM initiative to support the creation and use of very large contextualised language models for Norwegian (and in principle other Nordic languages), including a ready-to-use software environment, as well as an experience report for data preparation and training. This paper introduces the first large-scale monolingual language models for Norwegian, based on both the ELMo and BERT frameworks. In addition to detailing the training process, we present contrastive benchmark results on a suite of NLP tasks for Norwegian. For additional background and access to the data, models, and software, please see: http://norlm.nlpl.eu</abstract>
<identifier type="citekey">kutuzov-etal-2021-large</identifier>
<location>
<url>https://aclanthology.org/2021.nodalida-main.4/</url>
</location>
<part>
<date>2021-may 31–2 jun</date>
<extent unit="page">
<start>30</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large-Scale Contextualised Language Modelling for Norwegian
%A Kutuzov, Andrey
%A Barnes, Jeremy
%A Velldal, Erik
%A Øvrelid, Lilja
%A Oepen, Stephan
%Y Dobnik, Simon
%Y Øvrelid, Lilja
%S Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2021
%8 may 31–2 jun
%I Linköping University Electronic Press, Sweden
%C Reykjavik, Iceland (Online)
%F kutuzov-etal-2021-large
%X We present the ongoing NorLM initiative to support the creation and use of very large contextualised language models for Norwegian (and in principle other Nordic languages), including a ready-to-use software environment, as well as an experience report for data preparation and training. This paper introduces the first large-scale monolingual language models for Norwegian, based on both the ELMo and BERT frameworks. In addition to detailing the training process, we present contrastive benchmark results on a suite of NLP tasks for Norwegian. For additional background and access to the data, models, and software, please see: http://norlm.nlpl.eu
%U https://aclanthology.org/2021.nodalida-main.4/
%P 30-40
Markdown (Informal)
[Large-Scale Contextualised Language Modelling for Norwegian](https://aclanthology.org/2021.nodalida-main.4/) (Kutuzov et al., NoDaLiDa 2021)
ACL
- Andrey Kutuzov, Jeremy Barnes, Erik Velldal, Lilja Øvrelid, and Stephan Oepen. 2021. Large-Scale Contextualised Language Modelling for Norwegian. In Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), pages 30–40, Reykjavik, Iceland (Online). Linköping University Electronic Press, Sweden.