@inproceedings{varab-schluter-2020-danewsroom,
title = "{D}a{N}ewsroom: A Large-scale {D}anish Summarisation Dataset",
author = "Varab, Daniel and
Schluter, Natalie",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.831",
pages = "6731--6739",
abstract = "Dataset development for automatic summarisation systems is notoriously English-oriented. In this paper we present the first large-scale non-English language dataset specifically curated for automatic summarisation. The document-summary pairs are news articles and manually written summaries in the Danish language. There has previously been no work done to establish a Danish summarisation dataset, nor any published work on the automatic summarisation of Danish. We provide therefore the first automatic summarisation dataset for the Danish language (large-scale or otherwise). To support the comparison of future automatic summarisation systems for Danish, we include system performance on this dataset of strong well-established unsupervised baseline systems, together with an oracle extractive summariser, which is the first account of automatic summarisation system performance for Danish. Finally, we make all code for automatically acquiring the data freely available and make explicit how this technology can easily be adapted in order to acquire automatic summarisation datasets for further languages.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varab-schluter-2020-danewsroom">
<titleInfo>
<title>DaNewsroom: A Large-scale Danish Summarisation Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Varab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Dataset development for automatic summarisation systems is notoriously English-oriented. In this paper we present the first large-scale non-English language dataset specifically curated for automatic summarisation. The document-summary pairs are news articles and manually written summaries in the Danish language. There has previously been no work done to establish a Danish summarisation dataset, nor any published work on the automatic summarisation of Danish. We provide therefore the first automatic summarisation dataset for the Danish language (large-scale or otherwise). To support the comparison of future automatic summarisation systems for Danish, we include system performance on this dataset of strong well-established unsupervised baseline systems, together with an oracle extractive summariser, which is the first account of automatic summarisation system performance for Danish. Finally, we make all code for automatically acquiring the data freely available and make explicit how this technology can easily be adapted in order to acquire automatic summarisation datasets for further languages.</abstract>
<identifier type="citekey">varab-schluter-2020-danewsroom</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.831</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>6731</start>
<end>6739</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DaNewsroom: A Large-scale Danish Summarisation Dataset
%A Varab, Daniel
%A Schluter, Natalie
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F varab-schluter-2020-danewsroom
%X Dataset development for automatic summarisation systems is notoriously English-oriented. In this paper we present the first large-scale non-English language dataset specifically curated for automatic summarisation. The document-summary pairs are news articles and manually written summaries in the Danish language. There has previously been no work done to establish a Danish summarisation dataset, nor any published work on the automatic summarisation of Danish. We provide therefore the first automatic summarisation dataset for the Danish language (large-scale or otherwise). To support the comparison of future automatic summarisation systems for Danish, we include system performance on this dataset of strong well-established unsupervised baseline systems, together with an oracle extractive summariser, which is the first account of automatic summarisation system performance for Danish. Finally, we make all code for automatically acquiring the data freely available and make explicit how this technology can easily be adapted in order to acquire automatic summarisation datasets for further languages.
%U https://aclanthology.org/2020.lrec-1.831
%P 6731-6739
Markdown (Informal)
[DaNewsroom: A Large-scale Danish Summarisation Dataset](https://aclanthology.org/2020.lrec-1.831) (Varab & Schluter, LREC 2020)
ACL