Combining Linguistic and Statistical Knowledge Sources in Natural-Language Processing for ATIS

During the past year, signiicant improvements have been made in the natural-language processing technology used in the SRI ATIS spoken-language understanding system. The principal developments have been (1) the incorporation of information from the natural-language grammar and lexicon into a statistical language model that is used in both recognition and understanding, (2) implementation of a robust interpretation component that constructs queries out of grammatical fragments when an utterance cannot be analyzed as a single phrase or utterance, and (3) a new context mechanism for air travel planning that constructs an explicit model of the user's intended itinerary.