From linear story generation to branching story graphs

Story generation from photos

Traditionally, stories are considered to be made of a fabula and a discourse. The fabula is the chronological sequence of events happening in the story world. The discourse is the re-ordered sequence of tellings of those events. Most previous work on storytelling has focused on a fabula-driven pipeline, where the fabula is generated independently of and prior to the discourse. However, to creat...

Story Generation with Crowdsourced Plot Graphs

Story generation is the problem of automatically selecting a sequence of events that meet a set of criteria and can be told as a story. Story generation is knowledge-intensive; traditional story generators rely on a priori defined domain models about fictional worlds, including characters, places, and actions that can be performed. Manually authoring the domain models is costly and thus not sca...

Towards Evolutionary Story Generation

In this paper we describe on-going work on combining two existing models of computational creativity. The GENCAD model proposes the use of an evolutionary algorithm (EA) that uses a population of exemplars as a starting point for its search, unlike traditional EA's, which use a randomly-generated initial population. The EA, operating on this population, is then used to generate new potentially ...

Emergent Story Generation: Lessons from Improvisational Theater

An emergent approach to story generation by computer is characterized by a lack of predetermined plot and a focus on character interaction forming the material for stories. A potential problem is that no interesting story emerges. However, improvisational theater shows that – at least for human actors – a predetermined plot is not necessary for creating a compelling story. There are some princi...

Extol Story Generation