Conceptual Primitive Decomposition for Knowledge Sharing via Natural Language

Natural language is an ideal mode of interaction and knowledge sharing between intelligent computer systems and their human users. But a major problem that natural language interaction poses is linguistic variation, or the “paraphrase problem”: there are a variety of ways of referring to the same idea. This is a special problem for intelligent systems in domains such as information retrieval, where a query presented in natural language is matched against an ontology or knowledge base, particularly when its representation uses a vocabulary based in natural language. This paper proposes solutions to these problems in primitive decomposition methods that represent concepts in terms of structures reflecting low-level, embodied human cognition. We argue that this type of representation system engenders richer relations between natural language expressions and knowledge structures, enabling more effective interactive knowledge sharing.