Protoe: enhancing knowledge graph completion models with unsupervised type representation learning

HIGHLIGHTS

  • who: Yuxun Lu and Ryutaro Ichise from the Department of Informatics, School of Multidisciplinary Sciences, The Graduate University for Advanced National Institute of Informatics, Tokyo, Japan have published the paper: ProtoE: Enhancing Knowledge Graph Completion Models with Unsupervised Type Representation Learning, in the Journal: Information 2022, 13, 354. of 24/05/2022
  • what: The authors propose ProtoE an unsupervised method for learning implicit type and type constraint representations. The aim of this change is to keep the role of f base and g consistent.
  • how: Details of these two observations are described below . . .

     

    Logo ScioWire Beta black

    If you want to have access to all the content you need to log in!

    Thanks :)

    If you don't have an account, you can create one here.

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?