Putting RDF2vec in Order

08/11/2021
by   Jan Portisch, et al.
0

The RDF2vec method for creating node embeddings on knowledge graphs is based on word2vec, which, in turn, is agnostic towards the position of context words. In this paper, we argue that this might be a shortcoming when training RDF2vec, and show that using a word2vec variant which respects order yields considerable performance gains especially on tasks where entities of different classes are involved.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset