@inproceedings{nodland-2023-training,
title = "Training and Evaluating {N}orwegian Sentence Embedding Models",
author = "N{\o}dland, Bernt Ivar Utst{\o}l",
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-1.23",
pages = "228--237",
abstract = "We train and evaluate Norwegian sentence embedding models using the contrastive learning methodology SimCSE. We start from pre-trained Norwegian encoder models and train both unsupervised and supervised models. The models are evaluated on a machine-translated version of semantic textual similarity datasets, as well as binary classification tasks. We show that we can train good Norwegian sentence embedding models, that clearly outperform the pre-trained encoder models, as well as the multilingual mBERT, on the task of sentence similarity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nodland-2023-training">
<titleInfo>
<title>Training and Evaluating Norwegian Sentence Embedding Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bernt</namePart>
<namePart type="given">Ivar</namePart>
<namePart type="given">Utstøl</namePart>
<namePart type="family">Nødland</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>We train and evaluate Norwegian sentence embedding models using the contrastive learning methodology SimCSE. We start from pre-trained Norwegian encoder models and train both unsupervised and supervised models. The models are evaluated on a machine-translated version of semantic textual similarity datasets, as well as binary classification tasks. We show that we can train good Norwegian sentence embedding models, that clearly outperform the pre-trained encoder models, as well as the multilingual mBERT, on the task of sentence similarity.</abstract>
<identifier type="citekey">nodland-2023-training</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.23</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>228</start>
<end>237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training and Evaluating Norwegian Sentence Embedding Models
%A Nødland, Bernt Ivar Utstøl
%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 nodland-2023-training
%X We train and evaluate Norwegian sentence embedding models using the contrastive learning methodology SimCSE. We start from pre-trained Norwegian encoder models and train both unsupervised and supervised models. The models are evaluated on a machine-translated version of semantic textual similarity datasets, as well as binary classification tasks. We show that we can train good Norwegian sentence embedding models, that clearly outperform the pre-trained encoder models, as well as the multilingual mBERT, on the task of sentence similarity.
%U https://aclanthology.org/2023.nodalida-1.23
%P 228-237
Markdown (Informal)
[Training and Evaluating Norwegian Sentence Embedding Models](https://aclanthology.org/2023.nodalida-1.23) (Nødland, NoDaLiDa 2023)
ACL