Parallel stochastic grammar induction

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 algorit...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
1. Verfasser:	Kremer, S.C.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Algorithm design and analysis Bayesian methods Character generation Distributed computing Frequency Gold Induction generators Learning systems Stochastic processes Stochastic systems
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	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.
DOI:	10.1109/ICNN.1997.614003