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

Autor:	Tarau, Paul
Rok vydání:	2021
Předmět:	Computer Science - Programming Languages Computer Science - Artificial Intelligence Computer Science - Machine Learning Computer Science - Logic in Computer Science
Zdroj:	EPTCS 345, 2021, pp. 141-154
Druh dokumentu:	Working Paper
DOI:	10.4204/EPTCS.345.27
Popis:	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/ . Comment: In Proceedings ICLP 2021, arXiv:2109.07914
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2109.08291 Zobrazit plný text záznamu View this record from Arxiv