Compositional Generalization and Neuro-Symbolic Architectures

Savitha Sam Abraham, Marjan Alirezaie

Keywords: Compositional generalization, Neuro-symbolic AI, DeepProbLog, Word Problem Solving, Visual Relation Recognition

Abstract: Compositional generalization is the ability to understand novel combinations of known concepts. Although it is considered as an innate skill for humans, recent studies have shown that neural networks lack this characteristic. In this paper, we focus on compositional generalization with respect to the two specific tasks of word problem solving and visual relation recognition and propose a neuro-symbolic solution, using DeepProbLog, that addresses the problem of compositionality in state-of-the-art neural systems for these tasks.