Cognitive ScienceVolume 26, Issue 5 p. 609-651
Free Access
Symbolically speaking: a connectionist model of sentence production
Franklin Chang
First published: 11 February 2010
Citations: 88
The ability to combine words into novel sentences has been used to argue that humans have symbolic language production abilities. Critiques of connectionist models of language often center on the inability of these models to generalize symbolically (Fodor & Pylyshyn, 1988; Marcus, 1998). To address these issues, a connectionist model of sentence production was developed. The model had variables (role-concept bindings) that were inspired by spatial representations (Landau & Jackendoff, 1993). In order to take advantage of these variables, a novel dual-pathway architecture with event semantics is proposed and shown to be better at symbolic generalization than several variants. This architecture has one pathway for mapping message content to words and a separate pathway that enforces sequencing constraints. Analysis of the model's hidden units demonstrated that the model learned different types of information in each pathway, and that the model's compositional behavior arose from the combination of these two pathways. The model's ability to balance symbolic and statistical behavior in syntax acquisition and to model aphasic double dissociations provided independent support for the dual-pathway architecture.
Citing Literature
Download PDF
About Wiley Online Library
Privacy Policy
Terms of Use
Help & Support
Contact Us
Training and Support
DMCA & Reporting Piracy
Subscription Agents
Advertisers & Corporate Partners
Connect with Wiley
The Wiley Network
Wiley Press Room
Copyright © 1999-2021 John Wiley & Sons, Inc. All rights reserved
ReferencesRelatedInformationPDFPDFRequest permissionExport citationAdd to favoritesTrack citationTerms and Conditions of UseLearn more.