Saved in:
Bibliographic Details
Main Authors: van Krieken, Emile, Badreddine, Samy, Manhaeve, Robin, Giunchiglia, Eleonora
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.00532
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909242199375872
author van Krieken, Emile
Badreddine, Samy
Manhaeve, Robin
Giunchiglia, Eleonora
author_facet van Krieken, Emile
Badreddine, Samy
Manhaeve, Robin
Giunchiglia, Eleonora
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_00532
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ULLER: A Unified Language for Learning and Reasoning
van Krieken, Emile
Badreddine, Samy
Manhaeve, Robin
Giunchiglia, Eleonora
Artificial Intelligence
Machine Learning
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.
title ULLER: A Unified Language for Learning and Reasoning
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.00532