From subjective to objective metrics for evolutionary story narration using event permutations

  • Authors:

  • Kun Wang;Vinh Bui;Eleni Petraki;Hussein A. Abbass

  • Affiliations:

  • School of Engineering and IT, UNSW-Canberra, Australia;School of Engineering and IT, UNSW-Canberra, Australia;Faculty of Arts and Design, University of Canberra, Australia;School of Engineering and IT, UNSW-Canberra, Australia

  • Venue:
  • SEAL'12 Proceedings of the 9th international conference on Simulated Evolution and Learning
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The use of evolutionary computation to automatically narrate a story in a natural language, such as English, is a very daunting task. Two main challenges are addressed in this paper. First, how to represent a story in a form that is simple for evolution to work on? Second, how to evaluate stories using proper objective metrics? We address the first challenge by introducing a permutation-based linear representation that relies on capturing the events in a story in a genome, and on transforming any sequence represented by this genome into a valid story using a genotype-phenotype mapping. This mapping uses causal relationships in a story as constraints. The second challenge is addressed by conducting human-based experiments to collect subjective measurements of two categories of familiar and unfamiliar stories to the participants. The data collected from this exercise are then correlated with objective metrics that we designed to capture the quality of a story. Results reveal interesting relationships that are discussed in details in the paper.