PARSEC: a structured connectionist parsing system for spoken language

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.<<ETX>>

[1]  Alex Waibel,et al.  Robust connectionist parsing of spoken language , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[2]  Risto Miikkulainen,et al.  A Pdp Architecture for Processing Sentences With Relative Clauses , 1990, COLING.

[3]  Ajay Naresh Jain,et al.  Parsec: a connectionist learning architecture for parsing spoken language , 1992 .

[4]  Masaru Tomita,et al.  Parsing noisy sentences , 1988, COLING.

[5]  Alex Waibel,et al.  Continuous speech recognition using linked predictive neural networks , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[6]  Mark A. Fanty,et al.  Context-free parsing with connectionist networks , 1987 .

[7]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[8]  Steven Abney,et al.  Parsing By Chunks , 1991 .

[9]  Alex Waibel,et al.  JANUS: a speech-to-speech translation system using connectionist and symbolic processing strategies , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.