Published December 10, 2018 | Version v1
Dataset Open

Evaluation Framework tests on RDF2Vec

  • 1. University of Salerno
  • 2. Fraunhofer FIT
  • 3. Almaden Research Center

Description

The ZIP file contains the results of the tests run through the evaluation framework available at https://git.rwth-aachen.de/KGEmbedding/evaluationFramework executed on vectors produce by RDF2Vec combined with 11 different weighting techniques, described in 

Cochez, M., Ristoski, P., Ponzetto, S.P., Paulheim, H.:
Biased graph walks for RDF graph embeddings.
In: Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics (2017).

The framework tested the vectors upon Machine Learning tasks - classification, regression, and clustering - and semantic tasks - document modeling, semantic analogies, and entity relatedness. 

At the top level, there is a summary of the results, detailed in the inner folder. 

Files

Files (1.4 MB)

Name Size Download all
md5:de6fc1f908fa09dddd9e6e6cdd9b1932
1.4 MB Download