@inproceedings{cohen-etal-2021-wikisum,
title = "{W}iki{S}um: Coherent Summarization Dataset for Efficient Human-Evaluation",
author = "Cohen, Nachshon and
Kalinsky, Oren and
Ziser, Yftah and
Moschitti, Alessandro",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.28",
doi = "10.18653/v1/2021.acl-short.28",
pages = "212--219",
abstract = "Recent works made significant advances on summarization tasks, facilitated by summarization datasets. Several existing datasets have the form of coherent-paragraph summaries. However, these datasets were curated from academic documents that were written for experts, thus making the essential step of assessing the summarization output through human-evaluation very demanding. To overcome these limitations, we present a dataset based on article summaries appearing on the WikiHow website, composed of how-to articles and coherent-paragraph summaries written in plain language. We compare our dataset attributes to existing ones, including readability and world-knowledge, showing our dataset makes human evaluation significantly easier and thus, more effective. A human evaluation conducted on PubMed and the proposed dataset reinforces our findings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cohen-etal-2021-wikisum">
<titleInfo>
<title>WikiSum: Coherent Summarization Dataset for Efficient Human-Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nachshon</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oren</namePart>
<namePart type="family">Kalinsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yftah</namePart>
<namePart type="family">Ziser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Moschitti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent works made significant advances on summarization tasks, facilitated by summarization datasets. Several existing datasets have the form of coherent-paragraph summaries. However, these datasets were curated from academic documents that were written for experts, thus making the essential step of assessing the summarization output through human-evaluation very demanding. To overcome these limitations, we present a dataset based on article summaries appearing on the WikiHow website, composed of how-to articles and coherent-paragraph summaries written in plain language. We compare our dataset attributes to existing ones, including readability and world-knowledge, showing our dataset makes human evaluation significantly easier and thus, more effective. A human evaluation conducted on PubMed and the proposed dataset reinforces our findings.</abstract>
<identifier type="citekey">cohen-etal-2021-wikisum</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.28</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.28</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>212</start>
<end>219</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WikiSum: Coherent Summarization Dataset for Efficient Human-Evaluation
%A Cohen, Nachshon
%A Kalinsky, Oren
%A Ziser, Yftah
%A Moschitti, Alessandro
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F cohen-etal-2021-wikisum
%X Recent works made significant advances on summarization tasks, facilitated by summarization datasets. Several existing datasets have the form of coherent-paragraph summaries. However, these datasets were curated from academic documents that were written for experts, thus making the essential step of assessing the summarization output through human-evaluation very demanding. To overcome these limitations, we present a dataset based on article summaries appearing on the WikiHow website, composed of how-to articles and coherent-paragraph summaries written in plain language. We compare our dataset attributes to existing ones, including readability and world-knowledge, showing our dataset makes human evaluation significantly easier and thus, more effective. A human evaluation conducted on PubMed and the proposed dataset reinforces our findings.
%R 10.18653/v1/2021.acl-short.28
%U https://aclanthology.org/2021.acl-short.28
%U https://doi.org/10.18653/v1/2021.acl-short.28
%P 212-219
Markdown (Informal)
[WikiSum: Coherent Summarization Dataset for Efficient Human-Evaluation](https://aclanthology.org/2021.acl-short.28) (Cohen et al., ACL-IJCNLP 2021)
ACL
- Nachshon Cohen, Oren Kalinsky, Yftah Ziser, and Alessandro Moschitti. 2021. WikiSum: Coherent Summarization Dataset for Efficient Human-Evaluation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 212–219, Online. Association for Computational Linguistics.