Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Software . 2021
License: CC BY
Data sources: ZENODO
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Software . 2021
License: CC BY
Data sources: ZENODO
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Software . 2021
License: CC BY
Data sources: Datacite
versions View all 3 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

StanfordNER Gender-Classifier

Authors: Mareike Schumacher;

StanfordNER Gender-Classifier

Abstract

CRF-Classifier für automatische Annotation männlicher, weiblicher und neutraler Genderzuschreibungen in deutschsprachiger Literatur. Der Gender-Classifier kann mit dem Stanford Named Entity Recognizer zusammen genutzt werden. Das Modell wurde mit einem Trainingskorpus folgender Zusammensetzung trainiert: ca. 100.000 Tokens aus 25 Novellen des deutschen Novellenschatzes ca. 40.000 Tokens aus 10 Romanen des 18. Jahrhunderts ca. 40.000 Tokens aus 10 Romanen des 19. Jahrhunderts ca. 40.000 Tokens aus 10 Romanen des 20. Jahrhunderts ca. 40.000 Tokens aus 10 Romanen des 21. Jahrhunderts ca. 20.000 Tokens aus 5 Dramen des 18. Jahrhunderts ca. 20.000 Tokens aus 5 Dramen des 19. Jahrhunderts ca. 20.000 Tokens aus 5 Dramen des 20. Jahrhunderts ca. 7.000 Figurennamen aus 500 Dramen des 17.-20. Jahrhunderts (bereitgestellt von https://dracor.org) Getestet wurde das Modell mit 6 Novellen aus dem deutschen Novellenschatz, 8 Romanen aus den Jahrhunderten 18-21 und 3 Dramen von Caroline von Günderrode (1805), das Modell erreichte in den Tests einen durchschnittlichen overall F1-Score von 78,09%. Die Erkennung von Genderzuschreibungen in Novellen des 19. Jahrhunderts ist mit einem durchschnittlichen overall F1-Score von 85,52% am besten. In Romanen des 18.-21. Jahrhunderts beträgt die durchschnittliche Gesamterkennungsgenauigkeit (F1-Score) 72,83%. In Ausschnitten aus drei Dramen von Caroline von Günderode (publiziert 1805) erreicht der Gender-Classifier einen F1-Score von 75,53% Der Classifier wird laufend weiter entwickelt. Es handelt sich um eine Open-Beta-Version. Geplant ist z.B. die Aufnahme weiterer Gender-Kategorien, die nicht in das Binärschema männlich-weiblich fallen. Der Classifier wurde im Projekt m*w entwickelt. Der Classifier kann wie folgt verwendet werden: Laden Sie sich den Classifier herunter Laden Sie sich das Named-Entity-Recognition-Tool StanfordNER herunter Öffnen Sie den Stanford-Named-Entity-Recognizer wie auf der Webseite der Stanford NLP Group beschrieben Laden Sie über "Classifier" > "Load CRF from file" den Gender-Classifier in das Tool Wählen Sie über "File" > "Open File" ein Dokument, in dem Genderzuschreibungen annotiert werden sollen Klicken Sie auf "Run" Die annotierten Daten können über "File" > "Save tagged file as" gespeichert und weiter verwendet werden.

Keywords

Digital Humanities, Gender Studies, Gender, digitale Literaturwissenschaft, Named Entity Recognition, Natural Language Processing

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 426
    download downloads 71
  • citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    Powered byBIP!BIP!
  • 426
    views
    71
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
426
71
Related to Research communities
GOTRIPLE - Social Sciences and Humanities Discovery service