Learning Grammar in Confined Worlds

Spinks, Graham and Cartuyvels, Ruben and Moens, Marie-Francine

Abstract

In this position paper we argue that modern machine learning approaches fail to adequately address how grammar and common sense should be learned. State of the art language models achieve impressive results in a range of specialized tasks but lack underlying world understanding. We advocate for experiments with the use of abstract, confined world environments where agents interact with the emphasis on learning world models. Agents are induced to learn the grammar needed to navigate the environment, hence their grammar will be grounded in this abstracted world. We believe that this grounded grammar will therefore facilitate a more realistic, interpretable and human-like form of common sense.

Info