G-Rap: interactive text synthesis using recurrent neural network suggestions

Schlegel, Udo; Cakmak, Eren; Buchmüller, Juri F.; Keim, Daniel A.

G-Rap: interactive text synthesis using recurrent neural network suggestions

Dateien

Schlegel_2-xeqgxbhdkp799.pdfGröße: 269.51 KBDownloads: 338

Datum

2018

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

ESANN 2018 proceedings. 2018

Zusammenfassung

Finding the best neural network configuration for a given goal can be challenging, especially when it is not possible to assess the output quality of a network automatically. We present G-Rap, an interactive interface based on Visual Analytics principles for comparing outputs of multiple RNNs for the same training data. G-Rap enables an iterative result generation process that allows a user to evaluate the outputs with contextual statistics.

Fachgebiet (DDC)

004 Informatik

Schlagwörter

Deep Learning, Recurrent Neural Networks, Interactive Machine Learning

Konferenz

European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning : ESANN 2018, 25. Apr. 2018 - 27. Apr. 2018, Brügge, Belgien

Zitieren

ISO 690

SCHLEGEL, Udo, Eren CAKMAK, Juri F. BUCHMÜLLER, Daniel A. KEIM, 2018. G-Rap: interactive text synthesis using recurrent neural network suggestions. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning : ESANN 2018. Brügge, Belgien, 25. Apr. 2018 - 27. Apr. 2018. In: ESANN 2018 proceedings. 2018

BibTex

@inproceedings{Schlegel2018inter-42292,
  year={2018},
  title={G-Rap: interactive text synthesis using recurrent neural network suggestions},
  booktitle={ESANN 2018 proceedings},
  author={Schlegel, Udo and Cakmak, Eren and Buchmüller, Juri F. and Keim, Daniel A.}
}

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/123456789/42292">
    <dc:contributor>Buchmüller, Juri F.</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/42292/3/Schlegel_2-xeqgxbhdkp799.pdf"/>
    <dc:creator>Schlegel, Udo</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/42292/3/Schlegel_2-xeqgxbhdkp799.pdf"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dcterms:abstract xml:lang="eng">Finding the best neural network configuration for a given goal can be challenging, especially when it is not possible to assess the output quality of a network automatically. We present G-Rap, an interactive interface based on Visual Analytics principles for comparing outputs of multiple RNNs for the same training data. G-Rap enables an iterative result generation process that allows a user to evaluate the outputs with contextual statistics.</dcterms:abstract>
    <dcterms:title>G-Rap: interactive text synthesis using recurrent neural network suggestions</dcterms:title>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:creator>Buchmüller, Juri F.</dc:creator>
    <dc:contributor>Schlegel, Udo</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-05-09T13:34:10Z</dcterms:available>
    <dc:rights>terms-of-use</dc:rights>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Cakmak, Eren</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/42292"/>
    <dc:creator>Cakmak, Eren</dc:creator>
    <dc:language>eng</dc:language>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <dcterms:issued>2018</dcterms:issued>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-05-09T13:34:10Z</dc:date>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja