The presentation proposes an microservice-based architectural model for knowledge interchange between story generation systems in the interest of enhancing the interoperability and fostering the co-creation process.
2. John Bear is somewhat hungry.
John Bear wants to get some
berries. John Bear wants to get
near the blueberries. John Bear
walks from a cave entrance to
the bush by going through a
pass through a valley through a
meadow. John Bear takes the
blueberries. John Bear eats the
blueberries. The blueberries
are gone. John Bear is not very
hungry.
TALE-SPIN, 1977
3. Dave Striver loved the university. He loved its
ivy-covered clocktowers, its ancient and sturdy
brick, and its sun-splashed verdant greens and
eager youth. He also loved the fact that the
university is free of the stark unforgiving
trials of the business world — only this isn’t a
fact: academia has its own tests, and some are
as merciless as any in the marketplace. A prime
example is the dissertation defense: to earn the
PhD, to become a doctor, one must pass an oral
examination on one’s dissertation. This was a
test Professor Edward Hart enjoyed giving.
BRUTUS, 2000
4. In Computational Creativity
research, we study how to develop
software which can take on some of
the creative responsibility in arts
and science projects.
5. A story generator algorithm (SGA)
refers to a computational procedure
resulting in an artifact that can be
considered a story.
6.
7.
8.
9.
10.
11.
12. The simplest way of creating rich
and complex stories is using
different systems, generating
different types of content according
to their capabilities.
13. Many of the existing systems have
been designed as monoliths, which
make the collaboration between
them a really complex challenge.
This happens because almost every
system duplicates a considerable
part of the common storytelling
functions.
14. If every storytelling system break
its architecture into finer-grain
components, such as microservices,
these components could be used
separately and evolved
independently.
15. Establish a collaborative model that
allows the generation of better and
richer stories by combining different
capabilities.
16. Every story generator provides a set
of key operations in the form of
services, so that each system can be
considered as a module in the
overall structure.
17.
18. Propper is a story generation system
that creates Russian folktales
according to Propp's generation
rules.
These rules provide a very clear
description of how the folktales
morphology could be used for story
generation.
Propp, V. Morphology of the Folktale. 1928.
19. STellA is a story generation system
that mixes a non-constrained
simulation which produces world
states and narrative actions as
source material for stories.
The material is filtered and selected
later by a discourse generation step.
20. Charade is an affinities-based story
generation system which creates
stories after simulating the
evolution of a relationship between
two characters using their mutual
affinities.
21. Due to the fact that all these
systems existed prior to the
definition of the microservices
ecosystem, everyone can be
considered as a legacy system that
must be adapted to this new
purpose.
22. The role of the director entails the
orchestration of the whole system,
establishing the order in which
every system would make its part.
24. The real core of STellA is the last
stage, focused on the discourse
generation.
It is composed of a set of filters that
apply various rules and functions
related to suspense and narrative
tension curves.
25. The reasoning stage generates trees
of possible continuations for every
world state –called snapshots.
The filters are applied over the full
tree of solutions in order to select
the most feasible path, and the end
result is the generated story.
27. Story generation systems are
extremely heterogeneous, and so are
their models for knowledge
representation.
The case of STellA is not an
exception.
28. Concerning this point, the need for a
common representation arises.
Every published service must be
considered to provide system-
specific knowledge structure, so the
adaptation step must be performed
in the composer module.
32. • Shared knowledge model.
• Author emulated by director.
• Trade-off between canonical MSA
and model requirements.
• Story generation API Economy.
33. [1] Roy Thomas Fielding. Architectural styles and the design of network-
based software architectures. PhD thesis, University of California,
Irvine, 2000.
[2] Pablo Gervás. Story generator algorithms. In The Living Handbook of
Narratology. Hamburg University Press, 2012.
[3] Pablo Gervás. Propp's morphology of the folk tale as a grammar for
generation. In OASIcs- OpenAccess Series in Informatics, volume 32.
Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, 2013.
[4] Pablo Gervás. Reviewing propps story generation procedure in the
light of computational creativity. AISB 2014, 2014.
[5] Carlos León and Pablo Gervás. Creativity in story generation from
the ground up: non-deterministic simulation driven by narrative. In 5th
International Conference on Computational Creativity, ICCC, 2014.
[6] Gonzalo Méndez, Pablo Gervás, and Carlos León. A model of
character affinity for agent-based story generation. In 9th International
Conference on Knowledge, Information and Creativity Support Systems,
Limassol, Cyprus, volume 11, page 2014, 2014.
34. econcepc@ucm.es
Facultad de Informática
Universidad Complutense de
Madrid
pgervas@ucm.es
Instituto de Tecnología del
Conocimiento
Universidad Complutense de
Madrid
gmendez@ucm.es
Instituto de Tecnología del
Conocimiento
Universidad Complutense de
Madrid
36. This paper has been partially funded by the project IDiLyCo: Digital Inclusion, Language
and Communication, Grant. No. TIN2015-66655-R (MINECO/FEDER).