Sub-symbolic knowledge representation for evocative chat-bots

Abstract

A sub-symbolic knowledge representation oriented to the enhancement of chat bot interaction is proposed. The result of the technique is the introduction of a semantic sub-symbolic layer to a traditional ontology-based knowledge representation. This layer is obtained mapping the ontology concepts into a semantic space built through Latent Semantic Analysis (LSA) technique and it is embedded into a conversational agent. This choice leads to a chat-bot with evocative capabilities whose knowledge representation framework is composed of two areas: the rational and the evocative one. As a standard ontology we have chosen the well-founded WordNet lexical dictionary, while as chat-bot the ALICE architecture. Experimental trials involving four lexical categories of WordNet have been conducted, and an example of interaction is shown at the end of the paper. © 2008 Physica-Verlag Heidelberg.