Title :
A stochastic parts program and noun phrase parser for unrestricted text
Author :
Church, Kemth Ward
Author_Institution :
Bell Lab., Murray Hill, NJ, USA
Abstract :
A program that tags each word in an input sentence with the most likely part of speech has been written. The program uses a linear-time dynamic programming algorithm to find an assignment of parts of speech to words that optimizes the product of (a) lexical probabilities (probability of observing part of speech i given word i) and (b) contextual probabilities (probability of observing part of speech i given n following parts of speech). Program performance is encouraging; a 400-word sample is presented and is judged to be 99.5% correct
Keywords :
speech analysis and processing; speech recognition; contextual probabilities; input sentence; lexical probabilities; linear-time dynamic programming algorithm; noun phrase parser; program performance; stochastic parts program; unrestricted text; Filters; Lattices; Natural languages; Optical character recognition software; Speech analysis; Speech recognition; Speech synthesis; Stochastic processes; Synthesizers; Tagging;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location :
Glasgow
DOI :
10.1109/ICASSP.1989.266522
