Description of the tutorial

The intended length of the tutorial is half day, with plenty of practical content and examples. We plan to have an interactive session where both instructors and participants can engage in rich discussions on the topic. We will close with some time for discussion. Some familiarity on the matter is expected but otherwise this should not prevent potential attendees from coming.

The agenda consists of two main blocks (fundamentals and applications), and addresses the following main points:


  • Capturing meaning from text as word embeddings.
  • Knowledge graph embeddings.
  • Building a vecsigrafo – generating hybrid knowledge representations from text corpora and knowledge graphs.
  • Evaluating vecsigrafos beyond visual inspection and intrinsic methods.
  • Vecsigrafos for curating and interlinking knowledge graphs.


  • Applications in cross-lingual natural language processing.
  • Beyond text understanding: Cross-modal extensions.

Target application domains

  • Classic literature
  • Fake news detection
  • Scientific information management