The Markovian Language Network: steps toward a connectionist architecture for grammar induction

Author

Goertzel, Ben ; Goertzel, Gwen

Author_Institution

Dept. of Psychol., Western Australia Univ., Nedlands, WA, Australia

fYear

1995

fDate

35030

Firstpage

242

Lastpage

247

Abstract

A novel, modular connectionist architecture for grammar induction is proposed, the “Markovian Language Network” (MLN). Based on Zellig Harris´s (1989) theory of syntax, MLN would seem to be a plausible biological and psychological model. Modules for extraction of Markov information and for categorization are interlinked and are used for multiple purposes. MLN has not yet been fully implemented, but simple experiments have been conducted with a hybrid system. MLN is seen as a first step toward a complete connectionist implementation of Harrisian linguistics

Keywords

Markov processes; computational linguistics; grammars; neural net architecture; Harrisian linguistics; Markov information extraction modules; Markovian Language Network; biological model; categorization; grammar induction; modular connectionist architecture; psychological model; syntax; Art; Biological system modeling; Cognitive science; Computer architecture; Computer science; Data mining; Natural languages; Neural networks; Organizing; Psychology;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Information Systems, 1995. ANZIIS-95. Proceedings of the Third Australian and New Zealand Conference on

Conference_Location

Perth, WA

Print_ISBN

0-86422-430-3

Type

conf

DOI

10.1109/ANZIIS.1995.705748

Filename

705748