Embedding OWL ontologies
Project description
OWL2Vec-Star
OWL2Vec*: Embedding OWL ontologies
Free software: Apache-2.0 License
Documentation: https://owl2vec-star.readthedocs.io.
Features
OWL2Vec* v0.2.0 exposes a CLI with two subcommands, which allows you to perform two main programs.
Standalone
This command will embed one ontology. It can be configured by the configuration file default.cfg. See the examples and comments in default.cfg for the usage.
Running example:
$ owl2vec_star standalone --config_file default.cfg
Note: Different from the experimental codes, the standalone command has implemented all OWL ontology relevant procedures in python with Owlready, but it also allows the user to use pre-calculated annotations/axioms/entities/projection to generate the corpus.
Standalone Multi
This command will embed multiple ontologies into one language model, where the documents from multiple ontologies will be merged. One use case example is embedding all the conference relevant ontologies of the OAEI conference track at once.
Running example:
$ owl2vec_star standalone-multi --config_file default_multi.cfg
Note: Different from the standalone command, this command for multiple ontologies does NOT allow the pre-calculated or external annotations/axioms/entities/projection.
Publications
Main Reference
Jiaoyan Chen, Pan Hu, Ernesto Jimenez-Ruiz, Ole Magnus Holter, Denvar Antonyrajah, and Ian Horrocks. OWL2Vec*: Embedding of OWL ontologies. Machine Learning, Springer, 2021. [PDF] [@Springer] [Collection] [Codes for the computed results.]
Applications with OWL2Vec*
Jiaoyan Chen, Ernesto Jimenez-Ruiz, Ian Horrocks, Denvar Antonyrajah, Ali Hadian, Jaehun Lee. Augmenting Ontology Alignment by Semantic Embedding and Distant Supervision. European Semantic Web Conference, ESWC 2021. [PDF] [LogMap Matcher work]
Ashley Ritchie, Jiaoyan Chen, Leyla Jael Castro, Dietrich Rebholz-Schuhmann, Ernesto Jiménez-Ruiz. Ontology Clustering with OWL2Vec*. DeepOntonNLP ESWC Workshop 2021. [PDF]
Preliminary Publications
Case Studies
Data and codes for class membership prediction on the Healthy Lifestyles (HeLis) ontology, and class subsumption prediction on the food ontology FoodOn and the Gene Ontology (GO), are under the folder case_studies/.
Credits
Code under rdf2vec/, which mainly implement walking strategies over RDF graphs, is derived from pyRDF2Vec (version 0.0.3, last access: 03/2020).
This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template. Many thanks to Vincenzo Cutrona for preparing this package.
History
0.2.0 (2021-08-04)
First release on PyPI.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
