Dynamic, Non-Local Role Bindings and Inferencing in a Localist Network for Natural Language Understanding

This paper introduces a means to handle the critical problem of nonlocal role-bindingsin localist spreading-activation networks. Every conceptual node in the network broadcasts a stable, uniquely-identifying activation pattern, called its signature. A dynamic role-binding is created whena role's binding node has an activation that matches the bound concept's signature. Most importantly, signatures are propagated across long paths of nodes to handle the non-local role-bindings necessary forinferencing. Our localist network model, ROBIN (ROle Binding and Inferencing Network), uses signature activations to robustly representschemata role-bindings and thus perfonn the inferencing, plan/goal analysis, schema instantiation, word-sense disambiguation, anddynamic reinterpretation portions of the natural language understanding process.