Parsec: a connectionist learning architecture for parsing spoken language
Parsec: a connectionist learning architecture for parsing spoken language
A PDP architecture for processing sentences with relative clauses
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2
Continuous speech recognition using linked predictive neural networks
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
JANUS: a speech-to-speech translation system using connectionist and symbolic processing strategies
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Hi-index | 0.00 |
We present PARSEC-a system for generating connectionist parsing networks from example parses. PARSEC is not based on formal grammar systems and has been geared towards spoken language tasks. PARSEC networks exhibit three strengths important for application to speech processing: 1) they learn to parse, and generalize well compared to hand-coded grammars; 2) they tolerate several types of noise; 3) they can learn to use multimodal input. We present the PARSEC architecture, its training algorithms, and performance analyses along several dimensions that demonstrate PARSEC's features. We compare PARSEC's performance to that of traditional grammar-based parsing systems.