Abstract
In this paper we propose a process to extract summarization corpora from Wikipedia articles. Applied to the German language we create a corpus of 240,000 texts. We use ROUGE scores for the extraction and evaluation of our corpus. For this we provide a ROUGE metric implementation adapted to the German language. The extracted corpus is used to train three abstractive summarization models which we compare to different baselines. The resulting summaries sound natural and cover the input text very well. The corpus can be downloaded at https://github.com/domfr/GeWiki.- Anthology ID:
- 2020.lrec-1.821
- Volume:
- Proceedings of the Twelfth Language Resources and Evaluation Conference
- Month:
- May
- Year:
- 2020
- Address:
- Marseille, France
- Editors:
- Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 6651–6655
- Language:
- English
- URL:
- https://aclanthology.org/2020.lrec-1.821
- DOI:
- Bibkey:
- Cite (ACL):
- Dominik Frefel. 2020. Summarization Corpora of Wikipedia Articles. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6651–6655, Marseille, France. European Language Resources Association.
- Cite (Informal):
- Summarization Corpora of Wikipedia Articles (Frefel, LREC 2020)
- Copy Citation:
- PDF:
- https://aclanthology.org/2020.lrec-1.821.pdf
Export citation
@inproceedings{frefel-2020-summarization,
title = "Summarization Corpora of {W}ikipedia Articles",
author = "Frefel, Dominik",
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-1.821",
pages = "6651--6655",
abstract = "In this paper we propose a process to extract summarization corpora from Wikipedia articles. Applied to the German language we create a corpus of 240,000 texts. We use ROUGE scores for the extraction and evaluation of our corpus. For this we provide a ROUGE metric implementation adapted to the German language. The extracted corpus is used to train three abstractive summarization models which we compare to different baselines. The resulting summaries sound natural and cover the input text very well. The corpus can be downloaded at \url{https://github.com/domfr/GeWiki}.",
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="frefel-2020-summarization">
<titleInfo>
<title>Summarization Corpora of Wikipedia Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Frefel</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>In this paper we propose a process to extract summarization corpora from Wikipedia articles. Applied to the German language we create a corpus of 240,000 texts. We use ROUGE scores for the extraction and evaluation of our corpus. For this we provide a ROUGE metric implementation adapted to the German language. The extracted corpus is used to train three abstractive summarization models which we compare to different baselines. The resulting summaries sound natural and cover the input text very well. The corpus can be downloaded at https://github.com/domfr/GeWiki.</abstract>
<identifier type="citekey">frefel-2020-summarization</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.821</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6651</start>
<end>6655</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T Summarization Corpora of Wikipedia Articles %A Frefel, Dominik %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 frefel-2020-summarization %X In this paper we propose a process to extract summarization corpora from Wikipedia articles. Applied to the German language we create a corpus of 240,000 texts. We use ROUGE scores for the extraction and evaluation of our corpus. For this we provide a ROUGE metric implementation adapted to the German language. The extracted corpus is used to train three abstractive summarization models which we compare to different baselines. The resulting summaries sound natural and cover the input text very well. The corpus can be downloaded at https://github.com/domfr/GeWiki. %U https://aclanthology.org/2020.lrec-1.821 %P 6651-6655
Markdown (Informal)
[Summarization Corpora of Wikipedia Articles](https://aclanthology.org/2020.lrec-1.821) (Frefel, LREC 2020)
- Summarization Corpora of Wikipedia Articles (Frefel, LREC 2020)
ACL
- Dominik Frefel. 2020. Summarization Corpora of Wikipedia Articles. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6651–6655, Marseille, France. European Language Resources Association.