A Best-first Backward-chaining Search Strategy based on Learned Predicate Representations

Alexander Sakharov

Abstract

Inference methods for first-order logic are widely used in knowledge base engines. These methods are powerful but slow in general. Neural networks make it possible to rapidly approximate the truth values of ground atoms. A hybrid neural-symbolic inference method is proposed in this paper. It is a best-first search strategy for backward chaining. The strategy is based on neural approximations of the truth values of literals. This method is precise and the results are explainable. It speeds up inference by reducing backtracking.

Download


Paper Citation


in Harvard Style

Sakharov A. (2021). A Best-first Backward-chaining Search Strategy based on Learned Predicate Representations.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-484-8, pages 982-989. DOI: 10.5220/0010299209820989


in Bibtex Style

@conference{icaart21,
author={Alexander Sakharov},
title={A Best-first Backward-chaining Search Strategy based on Learned Predicate Representations},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2021},
pages={982-989},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010299209820989},
isbn={978-989-758-484-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - A Best-first Backward-chaining Search Strategy based on Learned Predicate Representations
SN - 978-989-758-484-8
AU - Sakharov A.
PY - 2021
SP - 982
EP - 989
DO - 10.5220/0010299209820989