NorQuAD: Norwegian Question Answering Dataset

Sardana Ivanova; Fredrik Andreassen; Matias Jentoft; Sondre Wold; Lilja Øvrelid

NorQuAD: Norwegian Question Answering Dataset

Sardana Ivanova, Fredrik Andreassen, Matias Jentoft, Sondre Wold, Lilja Øvrelid

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

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.

Original language	English
Title of host publication	Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
Number of pages	10
Publisher	University of Tartu Library
Publication date	May 2023
Pages	159-168
ISBN (Electronic)	978-9916-21-999-7
Publication status	Published - May 2023
MoE publication type	A4 Article in conference proceedings
Event	Nordic Conference on Computational Linguistics - Tórshavn, Faroe Islands Duration: 22 May 2023 → 24 May 2023 Conference number: 24

Publication series

Name	NEALT Proceedings Series
Publisher	University of Tartu Library
Number	52
ISSN (Electronic)	1736-6305

Fields of Science

113 Computer and information sciences
6121 Languages

Access to Document

NorQuADFinal published version, 313 KBLicence: CC BY

https://aclanthology.org/2023.nodalida-1.17Licence: CC BY

Cite this

@inproceedings{18cb6ca500264320a52b84ec28593475,

title = "NorQuAD: Norwegian Question Answering Dataset",

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.",

keywords = "113 Computer and information sciences, 6121 Languages",

author = "Sardana Ivanova and Fredrik Andreassen and Matias Jentoft and Sondre Wold and Lilja {\O}vrelid",

year = "2023",

month = may,

language = "English",

series = "NEALT Proceedings Series",

publisher = "University of Tartu Library",

number = "52",

pages = "159--168",

booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",

address = "Estonia",

note = "Nordic Conference on Computational Linguistics , NoDaLiDa 2023 ; Conference date: 22-05-2023 Through 24-05-2023",

}

Ivanova, S, Andreassen, F, Jentoft, M, Wold, S & Øvrelid, L 2023, NorQuAD: Norwegian Question Answering Dataset. in Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa). NEALT Proceedings Series, no. 52, University of Tartu Library, pp. 159-168, Nordic Conference on Computational Linguistics , Tórshavn, Faroe Islands, 22/05/2023. <https://aclanthology.org/2023.nodalida-1.17>

NorQuAD: Norwegian Question Answering Dataset. / Ivanova, Sardana; Andreassen, Fredrik; Jentoft, Matias et al.
Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa). University of Tartu Library, 2023. p. 159-168 (NEALT Proceedings Series; No. 52).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - NorQuAD: Norwegian Question Answering Dataset

AU - Ivanova, Sardana

AU - Andreassen, Fredrik

AU - Jentoft, Matias

AU - Wold, Sondre

AU - Øvrelid, Lilja

N1 - Conference code: 24

PY - 2023/5

Y1 - 2023/5

N2 - 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.

AB - 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.

KW - 113 Computer and information sciences

KW - 6121 Languages

M3 - Conference contribution

T3 - NEALT Proceedings Series

SP - 159

EP - 168

BT - Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)

PB - University of Tartu Library

T2 - Nordic Conference on Computational Linguistics

Y2 - 22 May 2023 through 24 May 2023

ER -