R. Michael Young

Narrative planning: balancing plot and character

Narrative, and in particular storytelling, is an important part of the human experience. Consequently, computational systems that can reason about narrative can be more effective communicators, entertainers, educators, and trainers. One of the central challenges in computational narrative reasoning is narrative generation, the automated creation of meaningful event sequences. There are many factors - logical and aesthetic - that contribute to the success of a narrative artifact. Central to this success is its understandability. We argue that the following two attributes of narratives are universal: (a) the logical causal progression of plot, and (b) character believability. Character believability is the perception by the audience that the actions performed by characters do not negatively impact the audiences suspension of disbelief. Specifically, characters must be perceived by the audience to be intentional agents. In this article, we explore the use of refinement search as a technique for solving the narrative generation problem - to find a sound and believable sequence of character actions that transforms an initial world state into a world state in which goal propositions hold. We describe a novel refinement search planning algorithm - the Intent-based Partial Order Causal Link (IPOCL) planner - that, in addition to creating causally sound plot progression, reasons about character intentionality by identifying possible character goals that explain their actions and creating plan structures that explain why those characters commit to their goals. We present the results of an empirical evaluation that demonstrates that narrative plans generated by the IPOCL algorithm support audience comprehension of character intentions better than plans generated by conventional partial-order planners.

A Use of Flashback and Foreshadowing for Surprise Arousal in Narrative Using a Plan-Based Approach

This paper describes work currently in progress to develop a computational method for generating flashback and foreshadowing, specifically targeted at the evocation of surprise in the readers mind. Flashback provides a backstory to explain what caused the surprise outcome. Foreshadowing provides an implicit hint about the surprise. Our study focuses on surprise as a cognitive response rather than as an emotional response. The readers story construction process is simulated by a plan-based reader model that checks unexpectedness and postdictability of the surprise.

DPOCL: a principled approach to discourse planning

Research in discourse processing has identified two representational requirements for discourse planning systems. First, discourse plans must adequately represent the intentional structure of the utterances they produce in order to enable a computational discourse agent to respond effectively to communicative failures [15]. Second, discourse plans must represent the informational structure of utterances. In addition to these representational requirements, we argue that discourse planners should be formally characterisable in terms of soundness and completeness.

Towards an architecture for intelligent control of narrative in interactive virtual worlds

The creation of novel, engaging and dynamic interactive stories presents a unique challenge to the designers of systems for interactive entertainment, education and training. Unlike conventional narrative media, an interactive narrative-based system may be required to generate its own story structure, determine the appropriate interface elements to use to convey the storys action and manage the effective interaction of a user within the story as it plays out. Here we describe the architecture of the Mimesis system, which integrates a 3D graphical gaming environment with intelligent techniques for generating and controlling interaction with and within a narrative in order to create an engaging and coherent user experience

Narrative Generation for Suspense: Modeling and Evaluation

Although suspense contributes significantly to the enjoyment of a narrative by its readers, there has been little research on the automated generation of stories that evoke specific cognitive and affective responses in their readers. The goal of this research is to develop and evaluate a system that produces a narrative designed specifically to evoke suspense from the reader. The system takes as input a plan data structure representing the goals of a storyworlds characters and the actions they perform in pursuit of them. Adapting theories developed by cognitive psychologists, the system uses a plan-based model of narrative comprehension to determine the final content of the story in order to heighten a readers level of suspense. This paper outlines the various components of the system and describes an empirical evaluation. The evaluation provides strong support for the claim that the system is effective in generating suspenseful stories.

Cinematic Visual Discourse: Representation, Generation, and Evaluation

In this paper, we present the design, implementation, and evaluation of an end-to-end camera planning system called Darshak. Darshak automatically constructs cinematic narrative discourse of a given story in a 3-D virtual environment. It utilizes a hierarchical partial-order causal link (POCL) planning algorithm to generate narrative plans that contain story events and camera directives for filming them. Dramatic situation patterns, commonly used by writers of fictional narratives, are formalized as communicative plan operators that provide a basis for structuring the cinematic content of the storys visualization. The dramatic patterns are realized through abstract communicative operators that represent operations on a viewers beliefs about the story and its telling. Camera shot compositions and transitions are defined in this plan-based framework as execution primitives. Darshaks performance is evaluated through a novel user study based on techniques used to evaluate existing cognitive models of narrative comprehension. Initial study reveals significant effect of the choice of visualization strategies on measured viewer comprehension. It further shows significant effect of Darshaks choice of visualization strategy on comprehension.

Story planning as exploratory creativity: Techniques for expanding the narrative search space

The authoring of fictional stories is considered a creative process. The purpose of most story authoring is not to invent a new style or genre of story that will be accepted by the population but to invent a single narrative that is novel enough to be tellable. Computational story generation systems are more limited than human authors in the space of narratives that can be considered because it is often the case that story generation systems are constrained to operate within a fixed representation of the story world. These limitations can impact whether a story generation system is considered creative or not. In this paper, we describe a story planning system, Fabulist. Fabulist however is constrained by the world model input by the system user. We present two algorithms that enable story planning systems such as Fabulist to break outside the bounds of the initial world model in order to search a larger space of narratives.

Real-time cinematic camera control for interactive narratives

Current 3D game engines offer the potential for new types of interactive storytelling. In this paper, we discuss automated cinematography as it relates to interactive narratives in virtual worlds. Due to the interactive nature of these environments, automated camera controllers cannot fully utilize all of the idioms in the domain of cinematography. It is important to note that substantial investigations into interactive cinematography have already been made [1, 2, 3]. In contrast to these individual systems, we propose a hybrid system that uses abstractly defined cinematographic idioms as constraints to choose the best camera placement for any shot at any moment within any geometry.

An objective character believability evaluation procedure for multi-agent story generation systems

The ability to generate narrative is of importance to computer systems that wish to use story effectively for entertainment, training, or education. One of the focuses of intelligent virtual agent research in general and story generation research in particular is how to make agents/characters more lifelike and compelling. However, one question that invariably comes up is: Is the generated story good? An easier question to tackle is whether a reader/viewer of a generated story perceives certain essential attributes such as causal coherence and character believability. Character believability is the perception that story world characters are acting according to their own beliefs, desires, and intentions. We present a novel procedure for objectively evaluating stories generated for multiple agents/characters with regard to character intentionality - an important aspect of character believability. The process transforms generated stories into a standardized model of story comprehension and then indirectly compares that representation to reader/viewer mental perceptions about the story. The procedure is illustrated by evaluating a narrative planning system, Fabulist.

Character-focused narrative generation for execution in virtual worlds

Because narrative plays such a key role in the understanding of events in our daily lives, the ability to generate narrative can be of great use in virtual reality systems whose purpose is to entertain, train, or educate their users. Narrative generation, however, is complicated by the conflicting goals of plot coherence – the appearance that events in the narrative lead towards the narrative’s outcome – and character believability – the appearance that events in the narrative are driven by the traits of the story world characters. Many systems are capable of achieving either one or the other; we present a new approach to narrative generation in the Actor Conference system, which is capable of generating narratives with both plot coherence and character believability. These narratives are declarative in nature, readily lending themselves to execution by embodied agents in virtual reality environments.