Natlog: a Lightweight Logic Programming Language with a Neuro-symbolic Touch

TL;DR

Natlog is a lightweight logic programming language that integrates symbolic reasoning with neural network-based content indexing, enabling seamless hybrid neuro-symbolic applications within the Python ecosystem.

Contribution

It introduces a simplified logic programming language with a neural network-compatible indexing mechanism, bridging symbolic and neural approaches.

Findings

Embedded in Python for easy integration

Supports neural delegation of indexing functions

Open-source and accessible as a Python package

Abstract

We introduce Natlog, a lightweight Logic Programming language, sharing Prolog's unification-driven execution model, but with a simplified syntax and semantics. Our proof-of-concept Natlog implementation is tightly embedded in the Python-based deep-learning ecosystem with focus on content-driven indexing of ground term datasets. As an overriding of our symbolic indexing algorithm, the same function can be delegated to a neural network, serving ground facts to Natlog's resolution engine. Our open-source implementation is available as a Python package at https://pypi.org/project/natlog/ .