Semantic Reasoning with Differentiable Graph Transformations

Code

• github.com/fractalego/dgt
  OfficialIn papernone★ 4

Abstract

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.

Reproductions