Controlling Search in Very large Commonsense Knowledge Bases: A Machine Learning Approach

TL;DR

This paper introduces machine learning heuristics to improve reasoning efficiency in large commonsense knowledge bases by prioritizing relevant inference paths, significantly reducing inference time.

Contribution

It presents two novel heuristics using decision trees and problem features to guide reasoning in large KBs, enhancing performance over traditional methods.

Findings

Order of magnitude reduction in inference time

Effective use of decision trees for inference step selection

Guidance from problem features improves search efficiency

Abstract

Very large commonsense knowledge bases (KBs) often have thousands to millions of axioms, of which relatively few are relevant for answering any given query. A large number of irrelevant axioms can easily overwhelm resolution-based theorem provers. Therefore, methods that help the reasoner identify useful inference paths form an essential part of large-scale reasoning systems. In this paper, we describe two ordering heuristics for optimization of reasoning in such systems. First, we discuss how decision trees can be used to select inference steps that are more likely to succeed. Second, we identify a small set of problem instance features that suffice to guide searches away from intractable regions of the search space. We show the efficacy of these techniques via experiments on thousands of queries from the Cyc KB. Results show that these methods lead to an order of magnitude reduction in inference time.