@inproceedings{pedersen-etal-2023-meda,
title = "{M}e{D}a-{BERT}: A medical {D}anish pretrained transformer model",
author = "Pedersen, Jannik and
Laursen, Martin and
Vinholt, Pernille and
Savarimuthu, Thiusius Rajeeth",
editor = {Alum{\"a}e, Tanel and
Fishel, Mark},
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may,
year = "2023",
address = "T{\'o}rshavn, Faroe Islands",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2023.nodalida-1.31",
pages = "301--307",
abstract = "This paper introduces a medical Danish BERT-based language model (MeDa-BERT) and medical Danish word embeddings. The word embeddings and MeDa-BERT were pretrained on a new medical Danish corpus consisting of 133M tokens from medical Danish books and text from the internet. The models showed improved performance over general-domain models on medical Danish classification tasks. The medical word embeddings and MeDa-BERT are publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pedersen-etal-2023-meda">
<titleInfo>
<title>MeDa-BERT: A medical Danish pretrained transformer model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jannik</namePart>
<namePart type="family">Pedersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Laursen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pernille</namePart>
<namePart type="family">Vinholt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thiusius</namePart>
<namePart type="given">Rajeeth</namePart>
<namePart type="family">Savarimuthu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanel</namePart>
<namePart type="family">Alumäe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tórshavn, Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a medical Danish BERT-based language model (MeDa-BERT) and medical Danish word embeddings. The word embeddings and MeDa-BERT were pretrained on a new medical Danish corpus consisting of 133M tokens from medical Danish books and text from the internet. The models showed improved performance over general-domain models on medical Danish classification tasks. The medical word embeddings and MeDa-BERT are publicly available.</abstract>
<identifier type="citekey">pedersen-etal-2023-meda</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.31</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>301</start>
<end>307</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MeDa-BERT: A medical Danish pretrained transformer model
%A Pedersen, Jannik
%A Laursen, Martin
%A Vinholt, Pernille
%A Savarimuthu, Thiusius Rajeeth
%Y Alumäe, Tanel
%Y Fishel, Mark
%S Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2023
%8 May
%I University of Tartu Library
%C Tórshavn, Faroe Islands
%F pedersen-etal-2023-meda
%X This paper introduces a medical Danish BERT-based language model (MeDa-BERT) and medical Danish word embeddings. The word embeddings and MeDa-BERT were pretrained on a new medical Danish corpus consisting of 133M tokens from medical Danish books and text from the internet. The models showed improved performance over general-domain models on medical Danish classification tasks. The medical word embeddings and MeDa-BERT are publicly available.
%U https://aclanthology.org/2023.nodalida-1.31
%P 301-307
Markdown (Informal)
[MeDa-BERT: A medical Danish pretrained transformer model](https://aclanthology.org/2023.nodalida-1.31) (Pedersen et al., NoDaLiDa 2023)
ACL
- Jannik Pedersen, Martin Laursen, Pernille Vinholt, and Thiusius Rajeeth Savarimuthu. 2023. MeDa-BERT: A medical Danish pretrained transformer model. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 301–307, Tórshavn, Faroe Islands. University of Tartu Library.