Generating Stories Using Role-playing Games and Simulated Human-like Conversations (original) (raw)
Related papers
Automatic generation of narrative content for digital games
2009
Interactive simulation games used for training usually require a large amount of coherent narrative content. An effective and efficient solution to the narrative content creation problem is to use Natural Language Generation (NLG) systems. The use of NLG systems, however, requires sophisticated linguistic and sometimes programming knowledge. For this reason, NLG systems are typically not accessible to the game designers who write narrative content. We have designed and implemented a visual environment for creating and modifying NLG templates that requires no programming knowledge, and can operate with a minimum of linguistic knowledge. It allows specifying templates with any number of variables and dependencies between them. It automatically generates all the sentences that follow the created template. It uses SimpleNLG to provide the linguistic background knowledge. We tested the performance of our system in the context of an interactive simulation game.
Supporting Dialogue Generation for Story-Based Games
Providing compelling, realistic, immersive game worlds is one of the major goals in modern game design. The presence of unique and interesting dialogue for all of the characters in a game enhances this sense of immersion. In this paper we present the concept of an "Intentional Dialogue Line" that supports the efficient generation of multiple variations of a dialogue, where these variations are both unique and appropriate to the character who is speaking them. This paper focuses on how machine learning can be used to quickly populate the intentional dialogue lines with existing content.
AISB Annual Convention, …, 2007
This paper presents a proposal for implementing automated story telling of narrative threads within a multiplayer game based on selection and linearization of game logs. Our initial prototype operates on logs generated artificially by a social simulation built by a multiagent system. This provides a log of events for a large set of characters emulating real life behaviour over a certain period of time, with no need to carry out a real game involving several players over an equivalent time. The proposed method addresses tasks of content determination -filtering the non-relevant events out of the total log -, and discourse planning -organizing a possibly large set of parallel threads of events into a linear narrative discourse. Actual sentence planning and realization is not addressed, but rather performed in a crude manner to allow readable presentation of the generated material. Examples of system input and output are presented, and their relative merits are discussed. The final section discusses futures lines of work that may be worth exploring. 2 Massive Multiplayer Online Role Playing Games
Planning-Based Narrative Generation in Simulated Game Universes
IEEE Transactions on Computational Intelligence and AI in Games, 2009
Agent-based social simulation is one way to add story to simulated game universes within the game mechanics while preserving the autonomy of non-play characters (NPCs). In this paper we add a social reasoning element behind NPC actions to make their plans more story-like. An AI planner is developed to combine plan search and logic inference about others' minds. An NPC agent equipped with the planner uses actions to change others' minds, and uses such mental changes to achieve its goal. We review the question whether stories do arise from agent-based simulations by examining actual narrative segments generated by our NPC agents, and by an experimental exploration of the frequencies and lengths of narrative segments. A story facilitator, named DIOS, makes stories happen when they are impossible via on-the-fly adjustment of character personalities.
Character-driven story generation in interactive storytelling
2001
Abstract We describe a fully implemented prototype for interactive storytelling using the Unreal TM engine. We describe the important mechanisms involved in the variability of plot instantiations, within a scenario of sitcom genre. We also provide an evaluation of the concepts of how the dynamic interactions between agents and/or the user influence the generation of story, with first results of examples
Generating Non-linear Narrative for Serious Games with Scenario Templates
2015
Complex social interactions between NPC's and players in a serious game remains a challenge. Standard game engines are focused on a game world with a fixed set of rules and linear gameplay. The problem is compounded by the unfamiliarity of many researchers with the basic structure and technicalities of a serious game. In this paper we propose a method to use linear scenario elements as templates for the generation of a non-linear narrative. We implement this method by creating an extra layer on top of the existing ATTAC-L modeling language which is a tool for developing virtual interactive scenarios. Users are thus presented with a language that offers limited flow control and simplifies the authoring process for the creation of scenario elements. Our method uses these existing scenario elements together with metadata, and fills in the templated elements with the contextual information of the current game state. By separating scenario concerns from non-linear narrative concerns, we hope to make it easier to develop interesting non-linear serious games that still conform to the requirements of evidence-based serious game research.
Toward supporting stories with procedurally generated game worlds
2011
Abstract Computer role playing games engage players through interleaved story and open-ended game play. We present an approach to procedurally generating, rendering, and making playable novel games based on a priori unknown story structures. These stories may be authored by humans or by computational story generation systems. Our approach couples player, designer, and algorithm to generate a novel game using preferences for game play style, general design aesthetics, and a novel story structure.
Novella: A Proposition for Game-Based Storytelling
2018
Video game narrative has many complexities that are difficult to capture due to the broad range of interactions the player may have and the numerous presentation methods found within games. While existing models of digital narrative do address interactivity, they do not always address the full breadth of agency available to players in games. We contribute a meta-analysis of select existing models in the context of video games, and present Novella, a new game-centric model of narrative intending to capture these difficulties.
Lume: A System for Procedural Story Generation
The Fourteenth International Conference on the Foundations of Digital Games (FDG ’19), August 26–30, 2019, San Luis Obispo, CA, USA, 2019
Procedural storytelling offers immense promise for games to offer more reactive narrative experiences that feel more deeply tailored to players' decisions. To date, interactive narrative systems have tended toward either a large emergent possibility space with less focus on narrative structure, or toward greater structure with smaller possibility spaces. In this paper, we introduce Lume, a system for procedural narrative generation that combines the best of these two approaches through a novel combinatorial scene architecture in which storylet scenes are comprised of parameterized node-trees. We detail how the system works and discuss how it moves toward creating reactive interactive narratives that are both dynamic and coherent. CCS CONCEPTS • Human-centered computing → Interactive systems and tools; Interaction design theory, concepts and paradigms; Systems and tools for interaction design; Hypertext / hypermedia.
Dialogue Generation in Character-based Interactive Storytelling
In recent years, there has been significant progress in developing Interactive Storytelling systems, in particular in terms of the underlying AI techniques. There has been an emerging consensus on the AI approach, in particular the use of planning systems. However, these have concentrated on the generation of a sequence of narrative actions, staged through the behaviour of virtual actors. In order to achieve the long-term objective of implementing interactive media that would reproduce the aesthetic qualities of traditional films, most interactive storytelling systems are still missing the ability to generate dialogues between characters. We describe an extension of our Interactive Storytelling approach which integrates dialogue generation within narrative situations. Our unit of generation is the dialogue act (pair of utterances) and one main objective is to reproduce realistic dialogue phenomena based on implicit forms of expression. The emphasis is also on adopting a unified approach relating narrative representations to the linguistic form of the generated utterances. From a representation of active narrative goals and the emotional affinity between characters, our system is able to derive a set of parameters governing various aspects of the linguistic form to be generated. We illustrate this approach on several implemented examples.