Today we’re joined by Mark Riedl, a Professor in the School of Interactive Computing at Georgia Tech.
Subscribe: iTunes / Google Play / Spotify / RSS
In our conversation with Mark, we explore his work building AI storytelling systems, mainly those that try and predict what listeners think will happen next in a story and how he brings together many different threads of ML/AI together to solve these problems. We discuss how the theory of mind is layered into his research, the use of large language models like GPT-3, and his push towards being able to generate suspenseful stories with these systems.
We also discuss the concept of intentional creativity and the lack of good theory on the subject, the adjacent areas in ML that he’s most excited about for their potential contribution to his research, his recent focus on model explainability, how he approaches problems of common sense, and much more!
Connect with Mark!
- Paper: Event Representations for Automated Story Generation with Deep Neural Nets
- Paper: Controllable Neural Story Plot Generation via Reinforcement Learning
- Paper: Story Realization: Expanding Plot Events into Sentences
- Paper: Automated Storytelling via Causal, Commonsense Plot Ordering
- Paper: Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions
- Paper: Fabula Entropy Indexing: Objective Measures of Story Coherence
- Paper: Situated Language Learning via Interactive Narratives
- Paper: Reducing Non-Normative Text Generation from Language Models
- Paper: Bringing Stories Alive: Generating Interactive Fiction Worlds
- Paper: Effect of Interaction Design of Reinforcement Learning Agents on Human Satisfaction in Partially Observable Domains
- Paper: Expanding Explainability: Towards Social Transparency in AI systems
- Paper: COMET: Commonsense Transformers for Automatic Knowledge Graph Construction