Strong systematicity in sentence processing by an echo state network

Authors:
Stefan L. Frank
Affiliations:
Nijmegen Institute for Cognition and Information, Radboud University Nijmegen, Nijmegen, The Netherlands
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Year:
2006

Citing 1
Cited 3

On The Proper Treatment of Semantic Systematicity

Minds and Machines

2007 Special Issue: Learning grammatical structure with Echo State Networks

Neural Networks
Syntactic systematicity in sentence processing with a recurrent self-organizing network

Neurocomputing
Improving the state space organization of untrained recurrent networks

ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

For neural networks to be considered as realistic models of human linguistic behavior, they must be able to display the level of systematicity that is present in language. This paper investigates the systematic capacities of a sentence-processing Echo State Network. The network is trained on sentences in which particular nouns occur only as subjects and others only as objects. It is then tested on novel sentences in which these roles are reversed. Results show that the network displays so-called strong systematicity.