Managing Multiple Knowledge Sources in Constraint-Based Parsing of Spoken Language

In this paper, we describe a system which is capable of utilizing a variety of knowledge sources to select the most appropriate parse for a spoken sentence. These knowledge sources include syntax, semantics, and contextual information. We discuss one way to utilize contextual information when determining a parse for a sentence. Our definition of a context is defined by which computer application we wish to interact with, where our system is capable of interfacing with two or more applications, each with a fixed vocabulary, syntax, and semanltics. The user is able to interact through a single interface which uses contextual knowledge not only to parse the query, but also to select the appropriate application to interact with. This birings us closer to developing a more general purpose interface for multiple applications.