Modelling Language, Action, and Perception in Type Theory with Records

Simon Dobnik, Robin Cooper, Staffan Larsson

Abstract: Formal models of natural language semantics using TTR (Type Theory with Records) attempt to relate natural language to perception, modelled as classification of objects and events by types which are available as resources to an agent. We argue that this is better suited for representing the meaning of spatial descriptions in the context of agent modelling than traditional formal semantic models which do not relate spatial concepts to perceptual apparatus. Spatial descriptions include perceptual, conceptual and discourse knowledge which we represent all in a single framework. Being a general framework for modelling both linguistic and non-linguistic cognition, TTR is more suitable for the modelling of situated conversational agents in robotics and virtual environments where interoperability between language, action and perception is required. The perceptual systems gain access to abstract conceptual meaning representations of language while the latter can be justified in action and perception.