Shadows and Headless Shadows: an Autobiographical Approach to Narrative Reasoning

TL;DR

This paper introduces the Xapagy architecture, a story-based cognitive system that uses autobiographical memory and shadowing mechanisms to perform reasoning, inference, and story generation.

Contribution

It presents a novel autobiographical approach to narrative reasoning using shadows and headless shadows within a cognitive architecture.

Findings

HLSs can track surprise levels in stories

HLSs enable inference of hidden actions and relations

HLSs support story recall and confabulation

Abstract

The Xapagy architecture is a story-oriented cognitive system which relies exclusively on the autobiographical memory implemented as a raw collection of events. Reasoning is performed by shadowing current events with events from the autobiography. The shadows are then extrapolated into headless shadows (HLSs). In a story following mood, HLSs can be used to track the level of surprise of the agent, to infer hidden actions or relations between the participants, and to summarize ongoing events. In recall mood, the HLSs can be used to create new stories ranging from exact recall to free-form confabulation.