OWL2Vec* v0.2.1

v0.2.1 supports installation and running by commands, as well as directly running by the original Python programs.

v0.2.1 has been upgraded with Python 3.8, gensim 4.x and RDFLib 6.0.0 supported and tested.

The following requirement is now supported:

Python 3.8
RDFLib 6.0.0
gensim 4.1.2
scikit-learn 0.24.2
nltk 3.6.7
OWLready2 0.25

A simple tutorial on accessing the embeddings (the class IRI vector and word vector) has been added in README.rst.

OWL2Vec* v0.1.0

Version used to compute the results in the Machine Learning journal paper:
Jiaoyan Chen, Pan Hu, Ernesto Jimenez-Ruiz, Ole Magnus Holter, Denvar Antonyrajah, and Ian Horrocks. OWL2Vec*: Embedding of OWL ontologies. Machine Learning, Springer, 2021

The codes in this version have been tested with
Python 3.7
RDFLib 4.2.2
gensim 3.8.0 (Note that gensim 4.x brings important changes)
scikit-learn 0.21.2
nltk 3.5
OWLready2 0.25

Codes under rdf2vec/, which mainly implement walking strategies over RDF graph, come from pyRDF2Vec (version 0.0.3, accessed in 03/2020), with some updates made.