Title :
Parallel stochastic grammar induction
Author :
Kremer, Stefan C.
Author_Institution :
Commun. Res. Centre, Ottawa, Ont., Canada
Abstract :
This paper examines the problem of stochastic grammar induction and gives a formal analysis of observed limitations of a classical algorithm. It then describes a parallel approach to the problem which avoids these limitations. Finally, a proof is presented which shows that a popular training algorithm already in use for recurrent connectionist networks implements the new approach
Keywords :
Bayes methods; formal languages; grammars; inference mechanisms; learning systems; minimisation; parallel processing; probability; recurrent neural nets; Bayes method; formal analysis; learning algorithm; learning systems; parallel processing; probability; recurrent connectionist networks; stochastic grammar induction; Algorithm design and analysis; Bayesian methods; Character generation; Distributed computing; Frequency; Gold; Induction generators; Learning systems; Stochastic processes; Stochastic systems;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.614003
