Spontaneous Analogy by Piggybacking on a Perceptual System
This addresses the challenge of spontaneous analogy for AI systems dealing with large-scale, unstructured data, though it is incremental in building on existing perceptual methods.
The paper tackles the problem of spontaneous analogy retrieval from large, unsegmented domains by representing relational structures as feature bags and leveraging perceptual algorithms to build an ontology and retrieve analogs efficiently. The result demonstrates significant time-savings over linear retrieval with a small accuracy cost in processing stories.
Most computational models of analogy assume they are given a delineated source domain and often a specified target domain. These systems do not address how analogs can be isolated from large domains and spontaneously retrieved from long-term memory, a process we call spontaneous analogy. We present a system that represents relational structures as feature bags. Using this representation, our system leverages perceptual algorithms to automatically create an ontology of relational structures and to efficiently retrieve analogs for new relational structures from long-term memory. We provide a demonstration of our approach that takes a set of unsegmented stories, constructs an ontology of analogical schemas (corresponding to plot devices), and uses this ontology to efficiently find analogs within new stories, yielding significant time-savings over linear analog retrieval at a small accuracy cost.