ML ASG Evaluation
Research on evaluating ML approaches to automated storytelling generation.
How do you assess a "good" story?
-
Can Machines Tell Stories? A Comparative Study of Deep Neural Language Models and Metrics -
Predicting Generated Story Quality with Quantitative Measures -
Quantitative Characteristics of Human-Written Short Stories as a Metric for Automated Storytelling -
Assessing the Novelty of Computer-Generated Narratives Using Empirical Metrics -
All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text
Computational creativity research
-
Computational Approaches to Storytelling and Creativity -
Some Empirical Criteria for Attributing Creativity to a Computer Program -
A preliminary framework for description, analysis and comparison of creative systems -
Evaluating Evaluation: Assessing Progress and Practices in Computational Creativity Research -
Computational Creativity and Systems -
A Standardised Procedure for Evaluating Creative Systems: Computational Creativity Evaluation Based on What it is to be Creative
Perplexity
-
usually the metric used for Language Modelling
-
Evaluation Metrics for Language Modelling - this is a very comprehensive article
Edited by Zala Sesko