ULLER: A Unified Language for Learning and Reasoning

TL;DR

ULLER introduces a unified language for neuro-symbolic AI, simplifying knowledge expression and comparison across frameworks, thereby enhancing accessibility and interoperability in the field.

Contribution

The paper presents ULLER, a comprehensive language that unifies diverse neuro-symbolic frameworks and supports multiple semantics, facilitating research and development.

Findings

ULLER covers classical, fuzzy, and probabilistic logics.

It enables compatibility with existing NeSy systems.

ULLER aims to streamline training and evaluation processes.

Abstract

The field of neuro-symbolic artificial intelligence (NeSy), which combines learning and reasoning, has recently experienced significant growth. There now are a wide variety of NeSy frameworks, each with its own specific language for expressing background knowledge and how to relate it to neural networks. This heterogeneity hinders accessibility for newcomers and makes comparing different NeSy frameworks challenging. We propose a unified language for NeSy, which we call ULLER, a Unified Language for LEarning and Reasoning. ULLER encompasses a wide variety of settings, while ensuring that knowledge described in it can be used in existing NeSy systems. ULLER has a neuro-symbolic first-order syntax for which we provide example semantics including classical, fuzzy, and probabilistic logics. We believe ULLER is a first step towards making NeSy research more accessible and comparable, paving the way for libraries that streamline training and evaluation across a multitude of semantics, knowledge bases, and NeSy systems.