Symbolically speaking: a connectionist model of sentence production
Article first published online: 11 FEB 2010
© 2002 Cognitive Science Society, Inc.
Volume 26, Issue 5, pages 609–651, September 2002
How to Cite
Chang, F. (2002), Symbolically speaking: a connectionist model of sentence production. Cognitive Science, 26: 609–651. doi: 10.1207/s15516709cog2605_3
- Issue published online: 11 FEB 2010
- Article first published online: 11 FEB 2010
- Received 10 September 2001; received in revised form 16 May 2002; accepted 28 May 2002
- Neural networks;
- Language acquisition;
- Cognitive architecture;
- Computer simulation
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.