Publikation:

Giveme5W1H : A Universal System for Extracting Main Events from News Articles

Vorschaubild

Dateien

Hamborg_2-1xyhp24n4a7n47.pdf
Hamborg_2-1xyhp24n4a7n47.pdfGröße: 624.38 KBDownloads: 196

Datum

2019

Autor:innen

Herausgeber:innen

Kontakt

ISSN der Zeitschrift

Electronic ISSN

ISBN

Bibliografische Daten

Verlag

Schriftenreihe

Auflagebezeichnung

URI (zitierfähiger Link)
http://nbn-resolving.de/urn:nbn:de:bsz:352-2-1xyhp24n4a7n47
DOI (zitierfähiger Link)
ArXiv-ID

Internationale Patentnummer

Link zur Lizenz

CC BY 4.0

Angaben zur Forschungsförderung

Projekt

Open Access-Veröffentlichung
Open Access Bookpart

Sammlungen

Informatik und Informationswissenschaft: Publikationen
Core Facility der Universität Konstanz

Gesperrt bis

Titel in einer weiteren Sprache

Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published

Erschienen in

ÖZGÖBEK, Özlem, ed., Benjamin KILLE, ed., Jon Atle GULLA, ed. and others. Proceedings of the 7th International Workshop on News Recommendation and Analytics. Aachen: CEUR, 2019, pp. 35-43. CEUR Workshop Proceedings. 2554. eISSN 1613-0073

Zusammenfassung

Event extraction from news articles is a commonly required prerequisite for various tasks, such as article summarization, article clustering, and news aggregation. Due to the lack of universally applicable and publicly available methods tailored to news datasets, many researchers redundantly implement event extraction methods for their own projects. The journalistic 5W1H questions are capable of describing the main event of an article, i.e., by answering who did what, when, where, why, and how. We provide an in-depth description of an improved version of Giveme5W1H, a system that uses syntactic and domain-specific rules to automatically extract the relevant phrases from English news articles to provide answers to these 5W1H questions. Given the answers to these questions, the system determines an article’s main event. In an expert evaluation with three assessors and 120 articles, we determined an overall precision of p=0.73, and p=0.82 for answering the first four W questions, which alone can sufficiently summarize the main event reported on in a news article. We recently made our system publicly available, and it remains the only universal open-source 5W1H extractor capable of being applied to a wide range of use cases in news analysis.

Zusammenfassung in einer weiteren Sprache

Fachgebiet (DDC)
004 Informatik

Schlagwörter

Konferenz

7th International Workshop on News Recommendation and Analytics, 20. Sept. 2020, Kopenhagen
Rezension
undefined / . - undefined, undefined

Forschungsvorhaben

Organisationseinheiten

Zeitschriftenheft

Zugehörige Datensätze in KOPS

Zitieren

ISO 690HAMBORG, Felix, Corinna BREITINGER, Bela GIPP, 2019. Giveme5W1H : A Universal System for Extracting Main Events from News Articles. 7th International Workshop on News Recommendation and Analytics. Kopenhagen, 20. Sept. 2020. In: ÖZGÖBEK, Özlem, ed., Benjamin KILLE, ed., Jon Atle GULLA, ed. and others. Proceedings of the 7th International Workshop on News Recommendation and Analytics. Aachen: CEUR, 2019, pp. 35-43. CEUR Workshop Proceedings. 2554. eISSN 1613-0073
BibTex
@inproceedings{Hamborg2019Givem-52761,
  year={2019},
  title={Giveme5W1H : A Universal System for Extracting Main Events from News Articles},
  url={http://ceur-ws.org/Vol-2554/paper_06.pdf},
  number={2554},
  publisher={CEUR},
  address={Aachen},
  series={CEUR Workshop Proceedings},
  booktitle={Proceedings of the 7th International Workshop on News Recommendation and Analytics},
  pages={35--43},
  editor={Özgöbek, Özlem and Kille, Benjamin and Gulla, Jon Atle},
  author={Hamborg, Felix and Breitinger, Corinna and Gipp, Bela}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/52761">
    <dc:rights>Attribution 4.0 International</dc:rights>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-02-09T08:15:03Z</dc:date>
    <dc:creator>Breitinger, Corinna</dc:creator>
    <dcterms:title>Giveme5W1H : A Universal System for Extracting Main Events from News Articles</dcterms:title>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Hamborg, Felix</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Gipp, Bela</dc:creator>
    <dc:contributor>Gipp, Bela</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/>
    <dcterms:abstract xml:lang="eng">Event extraction from news articles is a commonly required prerequisite for various tasks, such as article summarization, article clustering, and news aggregation. Due to the lack of universally applicable and publicly available methods tailored to news datasets, many researchers redundantly implement event extraction methods for their own projects. The journalistic 5W1H questions are capable of describing the main event of an article, i.e., by answering who did what, when, where, why, and how. We provide an in-depth description of an improved version of Giveme5W1H, a system that uses syntactic and domain-specific rules to automatically extract the relevant phrases from English news articles to provide answers to these 5W1H questions. Given the answers to these questions, the system determines an article’s main event. In an expert evaluation with three assessors and 120 articles, we determined an overall precision of p=0.73, and p=0.82 for answering the first four W questions, which alone can sufficiently summarize the main event reported on in a news article. We recently made our system publicly available, and it remains the only universal open-source 5W1H extractor capable of being applied to a wide range of use cases in news analysis.</dcterms:abstract>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Hamborg, Felix</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/52761"/>
    <dc:language>eng</dc:language>
    <dcterms:issued>2019</dcterms:issued>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/52761/1/Hamborg_2-1xyhp24n4a7n47.pdf"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-02-09T08:15:03Z</dcterms:available>
    <dc:contributor>Breitinger, Corinna</dc:contributor>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/52761/1/Hamborg_2-1xyhp24n4a7n47.pdf"/>
  </rdf:Description>
</rdf:RDF>

Interner Vermerk

xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter

Kontakt
URL der Originalveröffentl.
http://ceur-ws.org/Vol-2554/paper_06.pdf

Prüfdatum der URL

2020-10-27

Prüfungsdatum der Dissertation

Finanzierungsart

Kommentar zur Publikation

Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Diese Publikation teilen