Grounded models as a basis for intuitive and deductive reasoning: the acquisition of logical categories
Josefina Sierra-Santibáñez · European Conference on Artificial Intelligence · 2002
Grounded models differ from axiomatic theories in establishing explicit connections between language and reality that are learned through language games. This paper describes how grounded models are constructed by visually grounded autonomous agents playing different types of language games, and explains how they can be used for intuitive reasoning. It proposes a particular language game that can be used for simulating the generation of logical categories (such as negation, conjunction, disjunction, implication or equivalence), and describes some experiments in which a couple of visually grounded agents construct a grounded model that can be used for spatial reasoning.