Affordances in Grounded Language Learning
We present a novel methodology involving mappings between different modes of semantic representation. We propose distributional semantic models as a mechanism for representing the kind of world knowledge inherent in the system of abstract symbols characteristic of a sophisticated community of language users. Then, motivated by insight from ecological psychology, we describe a model approximating affordances, by which we mean a language learner{'}s direct perception of opportunities for action in an environment. We present a preliminary experiment involving mapping between these two representational modalities, and propose that our methodology can become the basis for a cognitively inspired model of grounded language learning.
PDF Abstract