Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Global RDF vector space embeddings

: Cochez, M.; Ristoski, P.; Ponzetto, S.P.; Paulheim, H.


D'Amato, C.:
The Semantic Web - ISWC 2017 : 16th International Semantic Web Conference, Vienna, Austria, October 21-25, 2017. Proceedings, Part I
Cham: Springer International Publishing, 2017 (Lecture Notes in Computer Science 10587)
ISBN: 978-3-319-68287-7
ISBN: 978-3-319-68288-4
International Semantic Web Conference (ISWC) <16, 2017, Vienna>
Conference Paper
Fraunhofer FIT ()

Vector space embeddings have been shown to perform well when using RDF data in data mining and machine learning tasks. Existing approaches, such as RDF2Vec, use local information, i.e., they rely on local sequences generated for nodes in the RDF graph. For word embeddings, global techniques, such as GloVe, have been proposed as an alternative. In this paper, we show how the idea of global embeddings can be transferred to RDF embeddings, and show that the results are competitive with traditional local techniques like RDF2Vec.