@inproceedings{mieskes-etal-2020-data,
title = "A Data Set for the Analysis of Text Quality Dimensions in Summarization Evaluation",
author = "Mieskes, Margot and
Loza Menc{\'\i}a, Eneldo and
Kronsbein, Tim",
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-1.826",
pages = "6690--6699",
abstract = "Automatic evaluation of summarization focuses on developing a metric to represent the quality of the resulting text. However, text qualityis represented in a variety of dimensions ranging from grammaticality to readability and coherence. In our work, we analyze the depen-dencies between a variety of quality dimensions on automatically created multi-document summaries and which dimensions automaticevaluation metrics such as ROUGE, PEAK or JSD are able to capture. Our results indicate that variants of ROUGE are correlated tovarious quality dimensions and that some automatic summarization methods achieve higher quality summaries than others with respectto individual summary quality dimensions. Our results also indicate that differentiating between quality dimensions facilitates inspectionand fine-grained comparison of summarization methods and its characteristics. We make the data from our two summarization qualityevaluation experiments publicly available in order to facilitate the future development of specialized automatic evaluation methods.",
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="mieskes-etal-2020-data">
<titleInfo>
<title>A Data Set for the Analysis of Text Quality Dimensions in Summarization Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Margot</namePart>
<namePart type="family">Mieskes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneldo</namePart>
<namePart type="family">Loza Mencía</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Kronsbein</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>Automatic evaluation of summarization focuses on developing a metric to represent the quality of the resulting text. However, text qualityis represented in a variety of dimensions ranging from grammaticality to readability and coherence. In our work, we analyze the depen-dencies between a variety of quality dimensions on automatically created multi-document summaries and which dimensions automaticevaluation metrics such as ROUGE, PEAK or JSD are able to capture. Our results indicate that variants of ROUGE are correlated tovarious quality dimensions and that some automatic summarization methods achieve higher quality summaries than others with respectto individual summary quality dimensions. Our results also indicate that differentiating between quality dimensions facilitates inspectionand fine-grained comparison of summarization methods and its characteristics. We make the data from our two summarization qualityevaluation experiments publicly available in order to facilitate the future development of specialized automatic evaluation methods.</abstract>
<identifier type="citekey">mieskes-etal-2020-data</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.826</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>6690</start>
<end>6699</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Data Set for the Analysis of Text Quality Dimensions in Summarization Evaluation
%A Mieskes, Margot
%A Loza Mencía, Eneldo
%A Kronsbein, Tim
%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 mieskes-etal-2020-data
%X Automatic evaluation of summarization focuses on developing a metric to represent the quality of the resulting text. However, text qualityis represented in a variety of dimensions ranging from grammaticality to readability and coherence. In our work, we analyze the depen-dencies between a variety of quality dimensions on automatically created multi-document summaries and which dimensions automaticevaluation metrics such as ROUGE, PEAK or JSD are able to capture. Our results indicate that variants of ROUGE are correlated tovarious quality dimensions and that some automatic summarization methods achieve higher quality summaries than others with respectto individual summary quality dimensions. Our results also indicate that differentiating between quality dimensions facilitates inspectionand fine-grained comparison of summarization methods and its characteristics. We make the data from our two summarization qualityevaluation experiments publicly available in order to facilitate the future development of specialized automatic evaluation methods.
%U https://aclanthology.org/2020.lrec-1.826
%P 6690-6699
Markdown (Informal)
[A Data Set for the Analysis of Text Quality Dimensions in Summarization Evaluation](https://aclanthology.org/2020.lrec-1.826) (Mieskes et al., LREC 2020)
ACL