Could the Road to Grounded, Neuro-symbolic AI be Paved with Words-as-Classifiers?
Preprint
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.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Cognitive modelling of concepts in the mental lexicon with multilayer networks: Insights, advancements, and future challengesPsychonomic Bulletin & Review, 2024
- Investigating preferential acquisition and attachment in early word learning through cognitive, visual and latent multiplex lexical networksPhysica A: Statistical Mechanics and its Applications, 2023
- Training Language Models to Follow Instructions with Human Feedback2022
- A Primer in BERTology: What We Know About How BERT WorksTransactions of the Association for Computational Linguistics, 2020
- Multiplex lexical networks reveal patterns in early word acquisition in childrenScientific Reports, 2017
- Formal semantics for perceptual classificationJournal of Logic and Computation, 2013
- Brain Cells for GrandmotherScientific American, 2013
- The symbol grounding problemPhysica D: Nonlinear Phenomena, 1990