Semantic Reasoning with Differentiable Graph Transformations

07/20/2021

∙

by   Alberto Cetoli, et al.

∙

18

∙

share

This paper introduces a differentiable semantic reasoner, where rules are presented as a relevant set of graph transformations. These rules can be written manually or inferred by a set of facts and goals presented as a training set. While the internal representation uses embeddings in a latent space, each rule can be expressed as a set of predicates conforming to a subset of Description Logic.