PARSEC: a structured connectionist parsing system for spoken language
- 1 January 1992
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 205-208 vol.1
- https://doi.org/10.1109/icassp.1992.225936
Abstract
The authors 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: they learn to parse, and generalize well compared to hand-coded grammars; they tolerate several types of noise; and they can learn to use multimodal input. The authors also present the PARSEC architecture, its training algorithms, and performance analyses along several dimensions that demonstrate PARSEC's features. They compare PARSEC's performance to that of traditional grammar-based parsing systems.<>Keywords
This publication has 6 references indexed in Scilit:
- Robust connectionist parsing of spoken languagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Continuous speech recognition using linked predictive neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- JANUS: a speech-to-speech translation system using connectionist and symbolic processing strategiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- A PDP architecture for processing sentences with relative clausesPublished by Association for Computational Linguistics (ACL) ,1990
- Representation and Structure in Connectionist ModelsPublished by Defense Technical Information Center (DTIC) ,1989
- Phoneme recognition using time-delay neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989