1 code implementation • 3 May 2024 • Simon Flügel, Martin Glauer, Till Mossakowski, Fabian Neuhaus
In order to increase the consistency of deep learning models, we propose a semantic loss that combines label-based loss with terms penalising subsumption- or disjointness-violations.
no code implementations • 7 Oct 2022 • Simon Flügel, Martin Glauer, Fabian Neuhaus, Janna Hastings
In ontology development, there is a gap between domain ontologies which mostly use the web ontology language, OWL, and foundational ontologies written in first-order logic, FOL.