Categorial grammars used to partial parsing of spoken language

Spoken language understanding is a challenge for the development of Spoken Dialogue Systems. Recognition errors and speech repairs make it impossible to get complete syntactic analysis. Shallow parsing and chunking seem to be efficient in order to start both a robust and precise analysis. This paper describes experiments made with Logus, a spoken understanding system based on incremental methology. It presents the first step of the parsing, a chunking based on rules of categorial grammars and pregroups. These formalisms are very appropriate for this treatment and we argue they could be more widely used for applications of this type.