@inproceedings{touileb-etal-2025-benchmarking,
title = "Benchmarking Abstractive Summarisation: {A} Dataset of Human-authored Summaries of {Norwegian} News Articles",
author = "Touileb, Samia and
Mikhailov, Vladislav and
Kroka, Marie Ingeborg and
{\O}vrelid, Lilja and
Velldal, Erik",
editor = "Johansson, Richard and
Stymne, Sara",
booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2025.nodalida-1.73/",
pages = "729--738",
ISBN = "978-9908-53-109-0",
abstract = "We introduce a dataset of high-quality human-authored summaries of news articles in Norwegian. The dataset is intended for benchmarking of the abstractive summarisation capabilities of generative language models. Each document in the dataset is provided with three different candidate gold-standard summaries written by native Norwegian speakers and all summaries are provided in both of the written variants of Norwegian {--} Bokm{\r{a}}l and Nynorsk. The paper describes details on the data creation effort as well as an evaluation of existing open LLMs for Norwegian on the dataset. We also provide insights from a manual human evaluation, comparing human-authored to model generated summaries. Our results indicate that the dataset provides a challenging LLM benchmark for Norwegian summarisation capabilities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="touileb-etal-2025-benchmarking">
<titleInfo>
<title>Benchmarking Abstractive Summarisation: A Dataset of Human-authored Summaries of Norwegian News Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="given">Ingeborg</namePart>
<namePart type="family">Kroka</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">Erik</namePart>
<namePart type="family">Velldal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Johansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-109-0</identifier>
</relatedItem>
<abstract>We introduce a dataset of high-quality human-authored summaries of news articles in Norwegian. The dataset is intended for benchmarking of the abstractive summarisation capabilities of generative language models. Each document in the dataset is provided with three different candidate gold-standard summaries written by native Norwegian speakers and all summaries are provided in both of the written variants of Norwegian – Bokmål and Nynorsk. The paper describes details on the data creation effort as well as an evaluation of existing open LLMs for Norwegian on the dataset. We also provide insights from a manual human evaluation, comparing human-authored to model generated summaries. Our results indicate that the dataset provides a challenging LLM benchmark for Norwegian summarisation capabilities.</abstract>
<identifier type="citekey">touileb-etal-2025-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2025.nodalida-1.73/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>729</start>
<end>738</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Abstractive Summarisation: A Dataset of Human-authored Summaries of Norwegian News Articles
%A Touileb, Samia
%A Mikhailov, Vladislav
%A Kroka, Marie Ingeborg
%A Øvrelid, Lilja
%A Velldal, Erik
%Y Johansson, Richard
%Y Stymne, Sara
%S Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)
%D 2025
%8 March
%I University of Tartu Library
%C Tallinn, Estonia
%@ 978-9908-53-109-0
%F touileb-etal-2025-benchmarking
%X We introduce a dataset of high-quality human-authored summaries of news articles in Norwegian. The dataset is intended for benchmarking of the abstractive summarisation capabilities of generative language models. Each document in the dataset is provided with three different candidate gold-standard summaries written by native Norwegian speakers and all summaries are provided in both of the written variants of Norwegian – Bokmål and Nynorsk. The paper describes details on the data creation effort as well as an evaluation of existing open LLMs for Norwegian on the dataset. We also provide insights from a manual human evaluation, comparing human-authored to model generated summaries. Our results indicate that the dataset provides a challenging LLM benchmark for Norwegian summarisation capabilities.
%U https://aclanthology.org/2025.nodalida-1.73/
%P 729-738
Markdown (Informal)
[Benchmarking Abstractive Summarisation: A Dataset of Human-authored Summaries of Norwegian News Articles](https://aclanthology.org/2025.nodalida-1.73/) (Touileb et al., NoDaLiDa 2025)
ACL