Evaluating the Pairwise Event Salience Hypothesis in Indexter

Authors

  • Christopher Kives University of New Orleans
  • Stephen Ware University of New Orleans
  • Lewis Baker Vanderbilt University

DOI:

https://doi.org/10.1609/aiide.v11i1.12789

Keywords:

Indexter, event-indexing situation models, EISM, salience, plan-based models of narrative, pairwise event salience hypothesis

Abstract

Indexter is a plan-based computational model of narrative discourse which leverages cognitive scientific theories of how events are stored in memory during online comprehension. These discourse models are valuable for static and interactive narrative generation systems because they allow the author to reason about the audience's understanding and attention as they experience a story. A pair of Indexter events can share up to five indices: protagonist, time, space, causality, and intentionality. We present the first in a planned series of evaluations that will explore increasingly nuanced methods of using these indices to predict salience. The Pairwise Event Salience Hypothesis states that when a past event shares one or more indices with the most recently narrated event, that past event is more salient than one which shares no indices with the most recently narrated event. A crowd-sourced (n=200) study of 24 short text stories that control for content, text, and length supports this hypothesis. While this is encouraging, we believe it also motivates the development of a richer model that accounts for intervening events, narrative complexity, and episodic memory decay.

Downloads

Published

2021-06-24

How to Cite

Kives, C., Ware, S., & Baker, L. (2021). Evaluating the Pairwise Event Salience Hypothesis in Indexter. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 11(1), 30-36. https://doi.org/10.1609/aiide.v11i1.12789