Parallel stochastic grammar induction
Stefan C. Kremer · Proceedings of International Conference on Neural Networks (ICNN'97) · 2002
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.