Spoken language processing in the hybrid connectionist architecture SCREEN

Abstract

In this paper we describe a robust, learning approach to spoken language understanding. Since interactively spoken and computationally analyzed language often contains many errors, robust connectionist networks are used for providing a flat screening analysis. A screening analysis is a shallow flat analysis based on category sequences at various syntactic, semantic and dialog levels. Rather than using tree or graph representations a screening analysis uses category sequences in order to support robustness and learning. This flat screening analysis is examined in the context of the system SCREEN (Symbolic Connectionist Robust EnterprisE for Natural language). Starting with the word hypotheses generated by a speech recognizer, we give an overview of the architecture, and illustrate the flat robust processing at the levels of syntax, semantics, and dialog acts. While early connectionist models were often limited to a single network and a small task, the hybrid connectionist SCREEN system is an important step towards exploring connectionist techniques in larger hybrid symbolic/connectionist environments and for real-world problemsBased on our experience with SCREEN, hybrid connectionist techniques show a lot of potential for supporting robustness in interactive spoken language processing.