Deductive and Analogical Reasoning on a Semantically Embedded Knowledge Graph

TL;DR

This paper introduces a novel method for deductive reasoning within a high-dimensional semantic vector space, enabling integration of analogy, association, and deduction from diverse knowledge sources.

Contribution

It presents a new approach to perform deductive reasoning directly in a continuous semantic vector space, combining multiple reasoning types seamlessly.

Findings

Enables reasoning directly in semantic vector space

Integrates analogy, association, and deduction

Draws on diverse knowledge sources

Abstract

Representing knowledge as high-dimensional vectors in a continuous semantic vector space can help overcome the brittleness and incompleteness of traditional knowledge bases. We present a method for performing deductive reasoning directly in such a vector space, combining analogy, association, and deduction in a straightforward way at each step in a chain of reasoning, drawing on knowledge from diverse sources and ontologies.