Narrative Fragment Creation: An Approach for Learning Narrative Knowledge

Storytelling is an integral part of the human experience, and understanding how stories or narratives are generated can offer insight into their importance. Current research focuses on the introduction of narrative knowledge into the generation process in order to facilitate the creation of qualitatively good narratives. Narrative generation and narrative knowledge, however, are two sides of the same coin; as knowledge about narrative events is necessary for generation, so is the ability to generate narratives indispensable to understanding the events therein. We propose the narrative fragment a construct intended to capture narrative knowledge and a method for automatically creating these fragments with narrative generation through partial order planning and analysis through n-gram modeling. The generated plans establish causal and temporal relationships, and by modeling those relationships and creating fragments, our system learns narrative knowledge.