SciPlore Xtract : Extracting Titles from Scientific PDF Documents by Analyzing Style Information (Font Size)

Beel, Jöran; Gipp, Bela; Shaker, Ammar; Friedrich, Nick

SciPlore Xtract : Extracting Titles from Scientific PDF Documents by Analyzing Style Information (Font Size)

Dateien

Beel_0-285747.pdfGröße: 197.85 KBDownloads: 678

Datum

2010

Autor:innen

Beel, Jöran

Gipp, Bela

Shaker, Ammar

Friedrich, Nick

Open Access-Veröffentlichung

Open Access Green

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

MOUNIA LALMAS, , ed. and others. Research and advanced technology for digital libraries :14th European Conference, ECDL 2010, Glasgow, UK, September 6 - 10, 2010; proceedings. Berlin [u.a.]: Springer, 2010, pp. 413-416. Lecture Notes in Computer Science. 6273. ISBN 978-3-642-15463-8. Available under: doi: 10.1007/978-3-642-15464-5_45

Zusammenfassung

Extracting titles from a PDF’s full text is an important task in information retrieval to identify PDFs. Existing approaches apply complicated and expensive (in terms of calculating power) machine learning algorithms such as Support Vector Machines and Conditional Random Fields. In this paper we present a simple rule based heuristic, which considers style information (font size) to identify a PDF’s title. In a first experiment we show that this heuristic delivers better results (77.9% accuracy) than a support vector machine by CiteSeer (69.4% accuracy) in an ‘academic search engine’ scenario and better run times (8:19 minutes vs. 57:26 minutes).

Fachgebiet (DDC)

004 Informatik

Schlagwörter

header extraction, title extraction, style information, document analysis

Konferenz

ECDL 2010, 6. Sep. 2010 - 10. Sep. 2010, Glasgow

Zitieren

ISO 690

BEEL, Jöran, Bela GIPP, Ammar SHAKER, Nick FRIEDRICH, 2010. SciPlore Xtract : Extracting Titles from Scientific PDF Documents by Analyzing Style Information (Font Size). ECDL 2010. Glasgow, 6. Sep. 2010 - 10. Sep. 2010. In: MOUNIA LALMAS, , ed. and others. Research and advanced technology for digital libraries :14th European Conference, ECDL 2010, Glasgow, UK, September 6 - 10, 2010; proceedings. Berlin [u.a.]: Springer, 2010, pp. 413-416. Lecture Notes in Computer Science. 6273. ISBN 978-3-642-15463-8. Available under: doi: 10.1007/978-3-642-15464-5_45

BibTex

@inproceedings{Beel2010SciPl-30892,
  year={2010},
  doi={10.1007/978-3-642-15464-5_45},
  title={SciPlore Xtract : Extracting Titles from Scientific PDF Documents by Analyzing Style Information (Font Size)},
  number={6273},
  isbn={978-3-642-15463-8},
  publisher={Springer},
  address={Berlin [u.a.]},
  series={Lecture Notes in Computer Science},
  booktitle={Research and advanced technology for digital libraries :14th European Conference, ECDL 2010, Glasgow, UK, September 6 - 10, 2010; proceedings},
  pages={413--416},
  editor={Mounia Lalmas},
  author={Beel, Jöran and Gipp, Bela and Shaker, Ammar and Friedrich, Nick}
}

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/123456789/30892">
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:title>SciPlore Xtract : Extracting Titles from Scientific PDF Documents by Analyzing Style Information (Font Size)</dcterms:title>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/30892/1/Beel_0-285747.pdf"/>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/30892"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2015-05-06T09:18:48Z</dcterms:available>
    <dc:rights>terms-of-use</dc:rights>
    <dc:creator>Shaker, Ammar</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Gipp, Bela</dc:contributor>
    <dc:contributor>Shaker, Ammar</dc:contributor>
    <dc:creator>Friedrich, Nick</dc:creator>
    <dc:language>eng</dc:language>
    <dc:creator>Gipp, Bela</dc:creator>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/30892/1/Beel_0-285747.pdf"/>
    <dcterms:abstract xml:lang="eng">Extracting titles from a PDF’s full text is an important task in information retrieval to identify PDFs. Existing approaches apply complicated and expensive (in terms of calculating power) machine learning algorithms such as Support Vector Machines and Conditional Random Fields. In this paper we present a simple rule based heuristic, which considers style information (font size) to identify a PDF’s title. In a first experiment we show that this heuristic delivers better results (77.9% accuracy) than a support vector machine by CiteSeer (69.4% accuracy) in an ‘academic search engine’ scenario and better run times (8:19 minutes vs. 57:26 minutes).</dcterms:abstract>
    <dc:creator>Beel, Jöran</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2015-05-06T09:18:48Z</dc:date>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:issued>2010</dcterms:issued>
    <dc:contributor>Beel, Jöran</dc:contributor>
    <dc:contributor>Friedrich, Nick</dc:contributor>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Nein