@inproceedings{ivanova-etal-2023-norquad,
title = "{N}or{Q}u{AD}: {N}orwegian Question Answering Dataset",
author = "Ivanova, Sardana and
Andreassen, Fredrik and
Jentoft, Matias and
Wold, Sondre and
{\O}vrelid, Lilja",
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-1.17",
pages = "159--168",
abstract = "In this paper we present NorQuAD: the first Norwegian question answering dataset for machine reading comprehension. The dataset consists of 4,752 manually created question-answer pairs. We here detail the data collection procedure and present statistics of the dataset. We also benchmark several multilingual and Norwegian monolingual language models on the dataset and compare them against human performance. The dataset will be made freely available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ivanova-etal-2023-norquad">
<titleInfo>
<title>NorQuAD: Norwegian Question Answering Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sardana</namePart>
<namePart type="family">Ivanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fredrik</namePart>
<namePart type="family">Andreassen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matias</namePart>
<namePart type="family">Jentoft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sondre</namePart>
<namePart type="family">Wold</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>
<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>In this paper we present NorQuAD: the first Norwegian question answering dataset for machine reading comprehension. The dataset consists of 4,752 manually created question-answer pairs. We here detail the data collection procedure and present statistics of the dataset. We also benchmark several multilingual and Norwegian monolingual language models on the dataset and compare them against human performance. The dataset will be made freely available.</abstract>
<identifier type="citekey">ivanova-etal-2023-norquad</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.17</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>159</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NorQuAD: Norwegian Question Answering Dataset
%A Ivanova, Sardana
%A Andreassen, Fredrik
%A Jentoft, Matias
%A Wold, Sondre
%A Øvrelid, Lilja
%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 ivanova-etal-2023-norquad
%X In this paper we present NorQuAD: the first Norwegian question answering dataset for machine reading comprehension. The dataset consists of 4,752 manually created question-answer pairs. We here detail the data collection procedure and present statistics of the dataset. We also benchmark several multilingual and Norwegian monolingual language models on the dataset and compare them against human performance. The dataset will be made freely available.
%U https://aclanthology.org/2023.nodalida-1.17
%P 159-168
Markdown (Informal)
[NorQuAD: Norwegian Question Answering Dataset](https://aclanthology.org/2023.nodalida-1.17) (Ivanova et al., NoDaLiDa 2023)
ACL
- Sardana Ivanova, Fredrik Andreassen, Matias Jentoft, Sondre Wold, and Lilja Øvrelid. 2023. NorQuAD: Norwegian Question Answering Dataset. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 159–168, Tórshavn, Faroe Islands. University of Tartu Library.