Spontaneous Analogy by Piggybacking on a Perceptual System

TL;DR

This paper introduces a system that automatically creates an ontology of relational structures from unsegmented stories, enabling spontaneous analogy retrieval from long-term memory with improved efficiency and minimal accuracy loss.

Contribution

It presents a novel approach that leverages perceptual algorithms to spontaneously retrieve analogs, addressing a gap in existing models that rely on predefined source and target domains.

Findings

Significant time savings in analog retrieval

Effective construction of an ontology of relational schemas

Maintains reasonable accuracy in analogy matching

Abstract

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.