CSC News

November 13, 2019

Team Wins Best Paper Award at AIIDE 2019

Congratulations to NC State Computer Science PhD graduate Justus Robertson and his co-authors Morteza Behrooz, a PhD student at University of California, Santa Cruz, and Arnav Jhala, associate professor of computer science at NC State, for winning the Best Student Paper Award at the 15th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE 2019) held in Atlanta, GA October 8-12, 2019.


The winning paper is “Story Quality as a Matter of Perception:  Using Word Embeddings to Estimate Cognitive Interest.”  The abstract follows:


Storytelling capability is an important tool for intelligent interactive agents for communication with human interactors.  Better storytelling capability can enable better interactions between humans and intelligent systems. For developing this skill, it is important to model what makes computationally generated stories interesting to humans. Existing metrics for story quality are either focused on textual features that are not necessarily reflective of perceived interestingness (eg coherence) or are domain-specific, relying on a priori semantic models (eg in games as templates for action sequences). However, the effectiveness of storytelling depends both on its versatility to adapt to new domains and the perceived interestingness of its generated stories. In this paper, drawing from cognitive science literature, we propose and evaluate a general computational method for estimating cognitive interest in stories based on the level of predictive inference they cause during perception.  


To read the winning paper, click here.


AIIDE 2019, sponsored by the Association for the Advancement of Artificial Intelligence (AAAI), brings together researchers and practitioners who work in AI for entertainment, including game designers, creative technologists, and media artists, and academic and industrial AI researchers.  This year’s conference featured a special theme of “Human-Centered Evaluation.”  In addition to general topics of interest in entertainment AI, the conference program featured speakers, panels, and paper sessions that focused on direct evaluation and critical analysis of AI in digital entertainment contexts.



Return To News Homepage