Presentation Open Access

Using deep learning to explore movement of people in a large corpus of biographies

Schlögl, Matthias; Lejtovicz, Katalin; Bernád, Ágoston Zénó; Kaiser, Maximilian; Rumpolt, Peter


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>In this presentation we showcase our first experiences with deep learning models for relation extraction in german biographies. These models are trained on human annotations of relations between the biographed person and entities found in the full-text (e.g. person A &gt;&gt; travelled to &gt;&gt; Wien).</p>\n\n<p>An interactive version of this presentation that allows also to test the trained model can be found <a href=\"https://apis.acdh.oeaw.ac.at/presentation_innsbruck17/\">here</a>.</p>", 
  "license": "http://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Austrian Academy of Sciences", 
      "@id": "https://orcid.org/0000-0003-1451-0987", 
      "@type": "Person", 
      "name": "Schl\u00f6gl, Matthias"
    }, 
    {
      "affiliation": "Austrian Academy of Sciences", 
      "@type": "Person", 
      "name": "Lejtovicz, Katalin"
    }, 
    {
      "affiliation": "Austrian Academy of Sciences", 
      "@type": "Person", 
      "name": "Bern\u00e1d, \u00c1goston Z\u00e9n\u00f3"
    }, 
    {
      "affiliation": "Austrian Academy of Sciences", 
      "@type": "Person", 
      "name": "Kaiser, Maximilian"
    }, 
    {
      "affiliation": "Austrian Academy of Sciences", 
      "@type": "Person", 
      "name": "Rumpolt, Peter"
    }
  ], 
  "url": "https://zenodo.org/record/1149023", 
  "datePublished": "2018-01-16", 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.1149023", 
  "@id": "https://doi.org/10.5281/zenodo.1149023", 
  "@type": "PresentationDigitalDocument", 
  "name": "Using deep learning to explore movement of people in a large corpus of  biographies"
}
47
32
views
downloads
All versions This version
Views 4747
Downloads 3232
Data volume 31.2 MB31.2 MB
Unique views 4141
Unique downloads 2929

Share

Cite as