Approaches to Grounding Symbols in Perceptual and Sensorimotor Categories

This chapter presents the Cognitive Symbol Grounding framework for the grounding of language into perception, cognition and action. This approach is characterized by the hypothesis that symbols are directly grounded in internal categorical representations, while at the same time having logical (e.g., syntactic) relationships with other symbols. The internal categorical representations, constituting the meanings upon which symbols are grounded, include perceptual, sensorimotor, and social categories, as well as internal state representations. Two main modeling approaches to the symbol grounding are presented: (i) the connectionist approach, based on artificial neural networks for category learning and naming tasks, and (ii) the embodied modeling approach, based on adaptive agent simulations and cognitive robots. These models provide an integrative view of the cognitive systems and help our understanding of the relationships between vision, action, and language.