An Essay concerning machine understanding

TL;DR

This paper explores how to construct machines capable of understanding by focusing on the relationship between words and underlying concepts, drawing on philosophical and psychological insights to guide the development of meaningful AI systems.

Contribution

It proposes a framework for machine understanding based on the association of words with concepts, integrating insights from philosophy and cognitivism to guide AI development.

Findings

Understanding involves recovering concepts behind words

Current models rely on constructing potential meanings

Experimental methods can assess machine understanding

Abstract

Artificial intelligence systems exhibit many useful capabilities, but they appear to lack understanding. This essay describes how we could go about constructing a machine capable of understanding. As John Locke (1689) pointed out words are signs for ideas, which we can paraphrase as thoughts and concepts. To understand a word is to know and be able to work with the underlying concepts for which it is an indicator. Understanding between a speaker and a listener occurs when the speaker casts his or her concepts into words and the listener recovers approximately those same concepts. Current models rely on the listener to construct any potential meaning. The diminution of behaviorism as a psychological paradigm and the rise of cognitivism provide examples of many experimental methods that can be used to determine whether and to what extent a machine might understand and to make suggestions about how that understanding might be instantiated.