Could the Road to Grounded, Neuro-symbolic AI be Paved with Words-as-Classifiers?

TL;DR

This paper explores the words-as-classifiers model as a promising approach to unify formal, distributional, and grounded semantics in AI, supported by literature review, cognitive science motivation, and a preliminary experiment.

Contribution

It proposes and motivates the words-as-classifiers model as a unifying framework for semantic theories, integrating formal, distributional, and grounded approaches.

Findings

The words-as-classifiers model has been successfully incorporated into language models.

Literature review supports its potential for semantic unification.

A small experiment demonstrates its practical applicability.

Abstract

Formal, Distributional, and Grounded theories of computational semantics each have their uses and their drawbacks. There has been a shift to ground models of language by adding visual knowledge, and there has been a call to enrich models of language with symbolic methods to gain the benefits from formal, distributional, and grounded theories. In this paper, we attempt to make the case that one potential path forward in unifying all three semantic fields is paved with the words-as-classifier model, a model of word-level grounded semantics that has been incorporated into formalisms and distributional language models in the literature, and it has been well-tested within interactive dialogue settings. We review that literature, motivate the words-as-classifiers model with an appeal to recent work in cognitive science, and describe a small experiment. Finally, we sketch a model of semantics unified through words-as-classifiers.