Towards a probabilistic, multi-layered spoken language interpretation system

Abstract

We present a preliminary report of a probabilistic spoken-language interpretation mechanism that is part of a dialogue system for an office assistant robot. We offer a probabilistic formulation for the generation of candidate interpretations and the selection of the interpretation with the highest posterior probability. This formulation is implemented in a multi-layered interpretation process that integrates spoken and sensory input, and takes into account alternatives derived from a user’s utterance and expectations obtained from the context. Our preliminary results are encouraging.