How can well tell that two people both have a concept of dog, gold, or car despite differences in their conceptual knowledge?  Two kinds of information can be used to translate between the concepts in two persons’ minds: the internal relations between concepts within each person’s mind, and external grounding of the concepts.  We present a neural network model called ABSURDIST (Aligning Between Systems Using Relations Derived Inside Systems Themselves) that integrates internal and external determinants of conceptual meaning to find translations across people or other systems.  The model shows that appropriate translations can be found by considering only similarity relations among concepts within a person.  However, simulations also indicate synergistic interactions between internal and external sources of information. ABSURDIST is then applied to analogical reasoning, dictionary translation, translating between web-based ontologies, subgraph matching, and object recognition.  The performance of ABSURDIST suggests the utility of concepts that are simultaneously externally grounded and enmeshed within a conceptual system.

Download PDF version of this paper