@inproceedings{schluter-2017-limits,
title = "The limits of automatic summarisation according to {ROUGE}",
author = "Schluter, Natalie",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 2, Short Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-2007",
pages = "41--45",
abstract = "This paper discusses some central caveats of summarisation, incurred in the use of the ROUGE metric for evaluation, with respect to optimal solutions. The task is NP-hard, of which we give the first proof. Still, as we show empirically for three central benchmark datasets for the task, greedy algorithms empirically seem to perform optimally according to the metric. Additionally, overall quality assurance is problematic: there is no natural upper bound on the quality of summarisation systems, and even humans are excluded from performing optimal summarisation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schluter-2017-limits">
<titleInfo>
<title>The limits of automatic summarisation according to ROUGE</title>
</titleInfo>
<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>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper discusses some central caveats of summarisation, incurred in the use of the ROUGE metric for evaluation, with respect to optimal solutions. The task is NP-hard, of which we give the first proof. Still, as we show empirically for three central benchmark datasets for the task, greedy algorithms empirically seem to perform optimally according to the metric. Additionally, overall quality assurance is problematic: there is no natural upper bound on the quality of summarisation systems, and even humans are excluded from performing optimal summarisation.</abstract>
<identifier type="citekey">schluter-2017-limits</identifier>
<location>
<url>https://aclanthology.org/E17-2007</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>41</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The limits of automatic summarisation according to ROUGE
%A Schluter, Natalie
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F schluter-2017-limits
%X This paper discusses some central caveats of summarisation, incurred in the use of the ROUGE metric for evaluation, with respect to optimal solutions. The task is NP-hard, of which we give the first proof. Still, as we show empirically for three central benchmark datasets for the task, greedy algorithms empirically seem to perform optimally according to the metric. Additionally, overall quality assurance is problematic: there is no natural upper bound on the quality of summarisation systems, and even humans are excluded from performing optimal summarisation.
%U https://aclanthology.org/E17-2007
%P 41-45
Markdown (Informal)
[The limits of automatic summarisation according to ROUGE](https://aclanthology.org/E17-2007) (Schluter, EACL 2017)
ACL
- Natalie Schluter. 2017. The limits of automatic summarisation according to ROUGE. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 41–45, Valencia, Spain. Association for Computational Linguistics.