research product . program source code . 2019

KGE Algorithms Knowledge Graph Embeddings with Type Regularizer

Kotnis, Bhushan (Department of Computational Linguistics, Heidelberg University, Germany (2016-2018), NEC Laboratories Europe GmbH (since 2018));
  • Published: 01 Jan 2019
  • Publisher: heiDATA
<p> An updated method for link prediction that uses a regularization factor that models relation argument types</p> <strong>Abstract (Kotnis and Nastase, 2017):</strong> </br> Learning relations based on evidence from knowledge repositories relies on processing the available relation instances. Knowledge repositories are not balanced in terms of relations or entities – there are relations with less than 10 but also thousands of instances, and entities involved in less than 10 but also thousands of relations. Many relations, however, have clear domain and range, which we hypothesize could help learn a better, more generalizing, model. We include such information ...
free text keywords: Arts and Humanities, Computer and Information Science, graph embedding, knowledge discovery in knowledge graphs, knowledge graphs, link prediction, Humanities
Digital Humanities and Cultural Heritage
Download from
program source code . 2019
Provider: B2FIND
Any information missing or wrong?Report an Issue