Abstract: A fundamental issue concerning the treatment of meaning in context is how to deal with the extremely flexible relationship that appears to hold between descriptions, which are taken as the exchangeable bearers of meaning, and the actual contexts which those descriptions are taken to pick out. Such contexts appear always only to be suggested, or constrained, by descriptions of contexts and so relating levels of description, such as linguistic utterances, to actual contexts of use, such as a situated, fully embodied environment in which language users find themselves, remains an unsolved challenge. The present article sets out a framework and illustrative implementation of an approach to contextualization that combines ontological engineering principles and situated embodied simulations. For concreteness, we illustrate the approach within an already established architecture for situated robotic agents in order to allow implementation and experimentation in a manner that is not generally accessible when considering linguistic analysis alone. The paper then proposes a hybrid, multi-level architecture that contextualizes linguistic utterances by means of embodied simulations, which then serve further as contextualization constraints on semantic interpretation.
Keywords: Embodiment, simulation, linguistic semantics, ontological analysis, formal ontology