Generalization Performance in PARSEC - A Structured Connectionist Parsing Architecture

Part of Advances in Neural Information Processing Systems 4 (NIPS 1991)

Bibtex Metadata Paper


Ajay Jain


This paper presents PARSEC-a system for generating connectionist parsing networks from example parses. PARSEC is not based on formal grammar systems and is geared toward spoken language tasks. PARSEC networks exhibit three strengths important for application to speech pro(cid:173) cessing: 1) they learn to parse, and generalize well compared to hand(cid:173) coded grammars; 2) they tolerate several types of noise; 3) they can learn to use multi-modal input. Presented are the PARSEC architecture and performance analyses along several dimensions that demonstrate PARSEC's features. PARSEC's performance is compared to that of tra(cid:173) ditional grammar-based parsing systems.