Creativity issues in plot generation

New Generation Computing, 2006

This paper presents an application that automatically generatesbasic stories: short texts that only narrate the main events of the plot. The system operates with a representation in Description Logics, combining stored fabulas with the narrative knowledge implemented in a domain-specific ontology. The domain of application is the traditional folk tale, using the well-known morphology of Vladimir Propp as narratological background. In order to evaluate the results, human judges blindly compared one of the generated basic stories to two alternatives: one rendered directly from a stored fabula of the knowledge base and another randomly generated. As a conclusion, possibilities of measuring the utility of the system in terms of quality and originality of the generated artifact are discussed.

2006

This paper presents an application that automatically generates basic stories: short texts that only narrate the main events of the plot. The system operates with a representation in Description Logics, combining stored fabulas with the narrative knowledge implemented in a domain-specific ontology. The domain of application is the traditional folk tale, using the well-known morphology of Vladimir Propp as narratological background. In order to evaluate the results, human judges blindly compared one of the generated basic stories to two alternatives: one rendered directly from a stored fabula of the knowledge base and another randomly generated. As a conclusion, possibilities of measuring the utility of the system in terms of quality and originality of the generated artifact are discussed.

Proceedings of the 2005 ACM SIGCHI International Conference on Advances in computer entertainment technology - ACE '05, 2005

A key issue in interactive storytelling is how to generate stories which are, at the same time, interesting and coherent. On the one hand, it is desirable to provide means for the user to intervene in the story. On the other hand, it is necessary to guarantee that user intervention will not introduce events that violate the rules of the intended genre. This paper describes LOGTELL, a tool we have been developing for interactively generating and dramatizing stories. We focus on the specification of a formal logic model for events and characters' behaviour. Based on the model, the user can interact with the tool at various levels, obtaining a variety of stories agreeable to individual tastes, within the imposed coherence requirements. The system alternates stages of goal inference, planning, user intervention and 3D visualization. Our experiments have shown that the system can be used not only for entertainment but also to help in the creation and adaptation of stories in conformity with a specified genre.

Cognitive Computation, 2015

The plots of stories are known to follow general patterns in terms of their overall structure. This was the basic tenet of structuralist approaches to narratology. Vladimir Propp proposed a procedure for the generation of new tales based on his semi-formal description of the structure of Russian folk tales. This is one of the first existing instances of a creative process described procedurally. The present paper revisits Propp’s morphology to build a system that generates instances of Russian folk tales. Propp’s view of the folk tale as a rigid sequence of character functions is employed as a plot driver, and some issues that Propp declared relevant but did not explore in detail—such as long-range dependencies between functions or the importance of endings—are given computational shape in the context of a broader architecture that captures all the aspects discussed by Propp. A set of simple evaluation metrics for the resulting outputs is defined inspired on Propp’s formalism. The p...

the 17th Joint …, 2005

2017

There are many different abstractions as to what a ’storytelling’ mechanism might be, each based on a particular understanding of what makes stories come together as a whole. Examples may be: archetypical instances of plot, story grammars, or the famous canonical sequence of character functions proposed by Vladimir Propp. From a computational point of view, each of these mechanisms can be used to construct or to validate new stories. The present paper carries out a comparative evaluation of a number of plot generation procedures, by grounding all of them on a basic reference vocabulary for the representation of narrative units, and applying to all of them a set of metrics distilled from the same procedures. The resulting set of computational tools is used in combination for comparative evaluation.

Vladimir Propp's analysis of Russian folk tales is known to have produced a semi-formal description of the structure of these tales that has acted as inspiration for several story generation systems, both sequential and interactive. Its exhaustive description of the constituent elements of tales of this kind, and the enumeration of the patterns they follow provided a very useful starting point for researchers looking for computational implementations of story generators. However, it is less generally known that in his book Propp also proposed a procedure for the generation of new tales based on his analytical framework. Although this generative procedure is much less formal than its analytical counterpart, it is one of the first existing instances of a creative process described procedurally. Of particular interest for the field of creative story generation is the number of issues that are declared relevant but not explored in detail. The present paper revisits Propp's description and focuses on the task of generating the sequence of character functions that determine the plot of the tale. For this task, a number of possible computational implementations are explored, in search for those that produce better results in terms of a number of simple evaluation metrics inspired by Propp's formalism.

IEEE Transactions on Computational Intelligence and AI in Games, 2016

Computers are often used as tools to design, implement and even visualize a variety of narrative forms. Many researchers and artists are now further attempting to engage the computer actively throughout the development of the narrative itself. Any form of computational narrative authoring is at some level always mixed-initiative, meaning that the processing capabilities of the computer are utilized with a varying degree to automate certain features of the authoring process. We structure this survey by focusing on two key components of stories, plot and space, and more specifically the degree to which these are either automated by the computer or authored manually. By examining the successes of existing research, we identify potential new research directions in the field of computational narrative. We also identify the advantages of developing a standard model of narrative to allow for collaboration between plot and space automation techniques. This would likely benefit the field of automated space generation with the strengths in the field of automated plot generation.

We introduce Slant, a system that integrates more than a decade of research into computational creativity, and specifically story generation, by connecting subsystems that deal with plot, figuration, and the narrative discourse using a blackboard. The process of integrating these systems highlights differences in the representation of story and has led to a better understanding of how story can be usefully abstracted. The plot generator MEXICA and a component of Curveship are used with little modification in Slant, while the figuration subsystem FigS and the template generator GRIOT-Gen, inspired by GRIOT, are also components. The development of the new subsystem Verso, which deals with genre, shows how different genres can be computationally modeled and applied to in-development stories to generate results that are surprising in terms of their connections and valuable in terms of their relationship to cultural questions. Example stories are discussed, as is the potential of the system to allow for broader collaboration, the empirical testing of how subsystems interrelate, and possible contributions in literary and artistic contexts.

2019

There have been a range of coding schemes to code story structure. However, few of these coding schemes map directly to expressive formal models of story that also characterize character beliefs or the complexities that arise when mistaken beliefs lead to action failure. We describe HeadCode, a coding scheme motivated by recent work in plan-based story generation.