Poznan University of Technology, Poznan, Poland
Jedrzej Potoniec is with Poznan University of Technology, Poznan, Poland, where he works as a researcher. He defended his Ph.D. in 2018 on learning ontologies from Linked Data. Currently, he is pursuing his research interests of building learning systems employing and/or outputting complex data structures like ontologies or business process models.
Talks and Events
Reason-able Embeddings: Learning Concept Embeddings with a Transferable Deep Neural Reasoner
We present a novel approach for learning embeddings of concepts from knowledge bases expressed in the ALC description logic. They reflect the semantics in such a way that it is possible to compute an embedding of a complex concept from the embeddings of its parts by using appropriate neural constructors. Embeddings for different knowledge bases are vectors in a shared vector space, shaped in such a way that approximate subsumption checking for arbitrarily complex concepts can be done by the same neural network for all the knowledge bases.
Track: Deep Learning for and with Knowledge Graphs
- Deep Learning for and with Knowledge Graphs