@inproceedings{hattasch-etal-2020-summarization,
title = "Summarization Beyond News: The Automatically Acquired Fandom Corpora",
author = {H{\"a}ttasch, Benjamin and
Geisler, Nadja and
Meyer, Christian M. and
Binnig, Carsten},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.827",
pages = "6700--6708",
abstract = "Large state-of-the-art corpora for training neural networks to create abstractive summaries are mostly limited to the news genre, as it is expensive to acquire human-written summaries for other types of text at a large scale. In this paper, we present a novel automatic corpus construction approach to tackle this issue as well as three new large open-licensed summarization corpora based on our approach that can be used for training abstractive summarization models. Our constructed corpora contain fictional narratives, descriptive texts, and summaries about movies, television, and book series from different domains. All sources use a creative commons (CC) license, hence we can provide the corpora for download. In addition, we also provide a ready-to-use framework that implements our automatic construction approach to create custom corpora with desired parameters like the length of the target summary and the number of source documents from which to create the summary. The main idea behind our automatic construction approach is to use existing large text collections (e.g., thematic wikis) and automatically classify whether the texts can be used as (query-focused) multi-document summaries and align them with potential source texts. As a final contribution, we show the usefulness of our automatic construction approach by running state-of-the-art summarizers on the corpora and through a manual evaluation with human annotators.",
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="hattasch-etal-2020-summarization">
<titleInfo>
<title>Summarization Beyond News: The Automatically Acquired Fandom Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Hättasch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadja</namePart>
<namePart type="family">Geisler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Meyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carsten</namePart>
<namePart type="family">Binnig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</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 Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Large state-of-the-art corpora for training neural networks to create abstractive summaries are mostly limited to the news genre, as it is expensive to acquire human-written summaries for other types of text at a large scale. In this paper, we present a novel automatic corpus construction approach to tackle this issue as well as three new large open-licensed summarization corpora based on our approach that can be used for training abstractive summarization models. Our constructed corpora contain fictional narratives, descriptive texts, and summaries about movies, television, and book series from different domains. All sources use a creative commons (CC) license, hence we can provide the corpora for download. In addition, we also provide a ready-to-use framework that implements our automatic construction approach to create custom corpora with desired parameters like the length of the target summary and the number of source documents from which to create the summary. The main idea behind our automatic construction approach is to use existing large text collections (e.g., thematic wikis) and automatically classify whether the texts can be used as (query-focused) multi-document summaries and align them with potential source texts. As a final contribution, we show the usefulness of our automatic construction approach by running state-of-the-art summarizers on the corpora and through a manual evaluation with human annotators.</abstract>
<identifier type="citekey">hattasch-etal-2020-summarization</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.827</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6700</start>
<end>6708</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Summarization Beyond News: The Automatically Acquired Fandom Corpora
%A Hättasch, Benjamin
%A Geisler, Nadja
%A Meyer, Christian M.
%A Binnig, Carsten
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth 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 hattasch-etal-2020-summarization
%X Large state-of-the-art corpora for training neural networks to create abstractive summaries are mostly limited to the news genre, as it is expensive to acquire human-written summaries for other types of text at a large scale. In this paper, we present a novel automatic corpus construction approach to tackle this issue as well as three new large open-licensed summarization corpora based on our approach that can be used for training abstractive summarization models. Our constructed corpora contain fictional narratives, descriptive texts, and summaries about movies, television, and book series from different domains. All sources use a creative commons (CC) license, hence we can provide the corpora for download. In addition, we also provide a ready-to-use framework that implements our automatic construction approach to create custom corpora with desired parameters like the length of the target summary and the number of source documents from which to create the summary. The main idea behind our automatic construction approach is to use existing large text collections (e.g., thematic wikis) and automatically classify whether the texts can be used as (query-focused) multi-document summaries and align them with potential source texts. As a final contribution, we show the usefulness of our automatic construction approach by running state-of-the-art summarizers on the corpora and through a manual evaluation with human annotators.
%U https://aclanthology.org/2020.lrec-1.827
%P 6700-6708
Markdown (Informal)
[Summarization Beyond News: The Automatically Acquired Fandom Corpora](https://aclanthology.org/2020.lrec-1.827) (Hättasch et al., LREC 2020)
ACL