ProtoPropp, the Fairy-Tale Generator

Federico Peinado, Pablo Gervás, Belén Díaz-Agudo and Raquel Hervás

ProtoPropp is an application of KIIDS that offers Automatic Generation of Russian Fairy Tales.

Example of a simple story from Alexander Afanasiev's collection of "Russian Fairy Tales".

The explosion of the information society and the various communication technologies have progressively shifted the bottleneck for the entertainment industry from technological issues to content production. Whether in the web site industry, the game industry, or the animation industry, companies employ larger numbers of screen writers and content providers than actual technicians or programmers (or devote higher portions of their budgets to buying ready made content elsewhere).

Automatic construction of story plots has always been a longed-for utopian dream in the entertainment industry, specially in the more commercial genres that are fueled by a large number of story plots with only a medium threshold on plot quality, such as TV series or video games. Although few professionals would contemplate full automation of the creative processes involved in plot writing, many would certainly welcome a fast prototyping tool that could produce a large number of acceptable plots involving a given set of initial circumstances or restrictions on the kind of characters that should be involved. Such a collection of plots might provide inspiration, initiate new ideas, or possibly even include a few plot sketches worthy of revision. Subsequent selection and revision of these plot sketches by professional screen writers could produce revised, fully human-authored valid plots. By making such a collection of tentative plots available to company screen writers, a smaller number of writers might be able to provide the material needed to keep the technical teams in work.

In order for an automated plot generation tool to meet the requirements described above, its results would have to exhibit a degree of unpredictability. In his work on story generation, Scott Turner advocates the use of CBR in plot generation to provide a level of automated ``creativity'' to systems of this kind.

In this project we propose a Knowledge-Intensive Case-Based Reasoning (KI-CBR) approach to the problem of generating story plots from a case base of existing stories analyzed in terms of Propp functions. A CBR process is defined to generate plots from a user query specifying an initial setting for the story, using an ontology to measure the semantical distance between words and structures taking part in the texts. This constitutes an improvement on previous work similar solutions had been applied to generate poetic texts using CBR but employing only syntactic information during adaptation.

ProppOnto is the ontology of ProtoPropp implemented in OWL with every narrative function defined by Vladimir Propp.

Meet the more modern version of our storyteller called Bard

Selected publications

Evaluation of Automatic Generation of Basic Stories (PDF)

Story Plot Generation based on CBR (PDF)

Creativity Issues in Plot Generation (PDF)

A Generative and Case-based Implementation of Proppian Morphology (PDF)

A Description Logic Ontology for Fairy Tale Generation (PDF)