@inproceedings{zopf-etal-2016-next,
title = "The Next Step for Multi-Document Summarization: A Heterogeneous Multi-Genre Corpus Built with a Novel Construction Approach",
author = "Zopf, Markus and
Peyrard, Maxime and
Eckle-Kohler, Judith",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1145",
pages = "1535--1545",
abstract = "Research in multi-document summarization has focused on newswire corpora since the early beginnings. However, the newswire genre provides genre-specific features such as sentence position which are easy to exploit in summarization systems. Such easy to exploit genre-specific features are available in other genres as well. We therefore present the new hMDS corpus for multi-document summarization, which contains heterogeneous source documents from multiple text genres, as well as summaries with different lengths. For the construction of the corpus, we developed a novel construction approach which is suited to build large and heterogeneous summarization corpora with little effort. The method reverses the usual process of writing summaries for given source documents: it combines already available summaries with appropriate source documents. In a detailed analysis, we show that our new corpus is significantly different from the homogeneous corpora commonly used, and that it is heterogeneous along several dimensions. Our experimental evaluation using well-known state-of-the-art summarization systems shows that our corpus poses new challenges in the field of multi-document summarization. Last but not least, we make our corpus publicly available to the research community at the corpus web page \url{https://github.com/AIPHES/hMDS}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zopf-etal-2016-next">
<titleInfo>
<title>The Next Step for Multi-Document Summarization: A Heterogeneous Multi-Genre Corpus Built with a Novel Construction Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Zopf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxime</namePart>
<namePart type="family">Peyrard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Judith</namePart>
<namePart type="family">Eckle-Kohler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Research in multi-document summarization has focused on newswire corpora since the early beginnings. However, the newswire genre provides genre-specific features such as sentence position which are easy to exploit in summarization systems. Such easy to exploit genre-specific features are available in other genres as well. We therefore present the new hMDS corpus for multi-document summarization, which contains heterogeneous source documents from multiple text genres, as well as summaries with different lengths. For the construction of the corpus, we developed a novel construction approach which is suited to build large and heterogeneous summarization corpora with little effort. The method reverses the usual process of writing summaries for given source documents: it combines already available summaries with appropriate source documents. In a detailed analysis, we show that our new corpus is significantly different from the homogeneous corpora commonly used, and that it is heterogeneous along several dimensions. Our experimental evaluation using well-known state-of-the-art summarization systems shows that our corpus poses new challenges in the field of multi-document summarization. Last but not least, we make our corpus publicly available to the research community at the corpus web page https://github.com/AIPHES/hMDS.</abstract>
<identifier type="citekey">zopf-etal-2016-next</identifier>
<location>
<url>https://aclanthology.org/C16-1145</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>1535</start>
<end>1545</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Next Step for Multi-Document Summarization: A Heterogeneous Multi-Genre Corpus Built with a Novel Construction Approach
%A Zopf, Markus
%A Peyrard, Maxime
%A Eckle-Kohler, Judith
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F zopf-etal-2016-next
%X Research in multi-document summarization has focused on newswire corpora since the early beginnings. However, the newswire genre provides genre-specific features such as sentence position which are easy to exploit in summarization systems. Such easy to exploit genre-specific features are available in other genres as well. We therefore present the new hMDS corpus for multi-document summarization, which contains heterogeneous source documents from multiple text genres, as well as summaries with different lengths. For the construction of the corpus, we developed a novel construction approach which is suited to build large and heterogeneous summarization corpora with little effort. The method reverses the usual process of writing summaries for given source documents: it combines already available summaries with appropriate source documents. In a detailed analysis, we show that our new corpus is significantly different from the homogeneous corpora commonly used, and that it is heterogeneous along several dimensions. Our experimental evaluation using well-known state-of-the-art summarization systems shows that our corpus poses new challenges in the field of multi-document summarization. Last but not least, we make our corpus publicly available to the research community at the corpus web page https://github.com/AIPHES/hMDS.
%U https://aclanthology.org/C16-1145
%P 1535-1545
Markdown (Informal)
[The Next Step for Multi-Document Summarization: A Heterogeneous Multi-Genre Corpus Built with a Novel Construction Approach](https://aclanthology.org/C16-1145) (Zopf et al., COLING 2016)
ACL