Narrative Generation System Research Articles

StoryForge: AI-Powered Narrative with Dynamic Imagery and Voice

StoryForge is an AI-powered narrative generation system that utilizes a combination of OpenAI’s GPT-3.5 Turbo model [1], Hugging Face’s Diffusion-based text-to-image gen- erative model Stable Diffusion XL (SDXL) [4], and Hugging Face’s Text-to-Speech Bark model [10] to create dynamic and engaging stories tailored to user-specified constraints. Users can input parameters such as genre, number of characters, character details, key events, mood, tone, point of view, and reader age to guide the narrative generation process. The system leverages the power of GPT-3.5 Turbo to generate the story text [1], SDXL to generate images for key events [4], and Bark to synthesize speech for the narrative [10], providing a comprehensive and immersive storytelling experience. A Streamlit-based user interface enables seamless interaction with the system, allowing users to input constraints, view generated text and images, and listen to the synthesized audio. It transforms user inputs into a multisen- sory narrative experience, marking a significant stride in the intersection of artificial intelligence and imaginative storytelling. StoryForge demonstrates the potential of AI to revolutionize storytelling, empowering users to create personalized and cap- tivating narratives with ease and embark on a journey where words, images, and voices converge to create truly one-of-a-kind tales. Index Terms—StoryForge, GPT-3.5 Turbo, Bark, Stable Dif- fusion XL, Streamlit, Hugging Face, Generative Model, Story- telling, Multisensory

Adjective and Adjective Verb Conceptual Dictionaries in an Integrated Narrative Generation System

Adjective and Adjective Verb Conceptual Dictionaries in an Integrated Narrative Generation System

Integrating Formal Qualitative Analysis Techniques within a Procedural Narrative Generation System

Qualitative analysis of procedurally generated narratives remains a difficult hurdle for most narrative generation tools. Typical analysis involves the use of human studies, rating the quality of the generated narratives against a given set of criteria, a costly and time consuming process. In this paper we integrate a set of features within the ReGEN system which aim to ensure narrative correctness and quality. Correct generation is ensured by performing an analysis of the preconditions and postconditions of each narrative event. Narrative quality is ensured by using an existing set of formal metrics which relate quality to the structure of the narrative to guide narrative generation. This quantitative approach provides an objective means of guaranteeing quality within narrative generation.

An Empirical Evaluation of a Generative Method for the Expression of Personality Traits through Action Choice

The presence of interesting and compelling characters is an essential component of effective narrative. Well-developed characters have features that enable them to significantly enhance the believability and quality of a story. In this paper, we describe the results of an experiment to evaluate a planning-based narrative generation system that focuses on the generation of stories that express character. The system is designed to automatically produce narratives that show character personality traits through the choices characters make when selecting the means by which they achieve their goals. Results from our study support the hypothesis that an audience presented with stories generated by Mask will attribute personality traits to the story characters that have significant correlation with the computational model of personality used to drive the characters' choices.

Character Beliefs in Story Generation

Character beliefs play a central role in many narratives, but are often not represented in planning-based author-centered narrative generation systems, or only represented in an ad hoc way. In this paper we will discuss how actions in Dynamic Epistemic Logic that affect the story world as well as the characters' beliefs, can be used in the context of narrative generation. By using this logical foundation we can ensure that the actors' beliefs are maintained in a logically consistent way, but we will also discuss how our system supports writing these complex logical operations in a concise way. We will also show how our system, which has limited planning capabilities, can come up with simple stories that cause characters to have beliefs desired by the author, and how our approach can be integrated with other work in the field.

Evaluating the Pairwise Event Salience Hypothesis in Indexter

Indexter is a plan-based computational model of narrative discourse which leverages cognitive scientific theories of how events are stored in memory during online comprehension. These discourse models are valuable for static and interactive narrative generation systems because they allow the author to reason about the audience's understanding and attention as they experience a story. A pair of Indexter events can share up to five indices: protagonist, time, space, causality, and intentionality. We present the first in a planned series of evaluations that will explore increasingly nuanced methods of using these indices to predict salience. The Pairwise Event Salience Hypothesis states that when a past event shares one or more indices with the most recently narrated event, that past event is more salient than one which shares no indices with the most recently narrated event. A crowd-sourced (n=200) study of 24 short text stories that control for content, text, and length supports this hypothesis. While this is encouraging, we believe it also motivates the development of a richer model that accounts for intervening events, narrative complexity, and episodic memory decay.

A Good Story Is One in a Million: Solution Density in Narrative Generation Problems

Narrative generation systems can be classified on a spectrum from strong autonomy to strong story. Systems on the strong autonomy side treat characters as fully independent agents but may struggle to meet the author’s requirements, while those on the strong story side direct character behaviors centrally but may struggle to create the illusion of character believability. In this paper, we use benchmark story generation problems as a framework to compare the spaces of stories that could be generated by prototypical strong story and strong autonomy systems. Comparing the relative solution densities of these spaces helps us quantify how common certain desirable narrative properties are. This can be informative for system designers when deciding, for instance, whether to strictly enforce all desired properties or to generate and filter from a broader class of solutions.

統合物語生成システムと「Creative Genome」を利用した広告プロット生成手法の一案

統合物語生成システムと「Creative Genome」を利用した広告プロット生成手法の一案

A Framework for Haiku Generation from a Narrative

The primary goal of the authors’ research related to the generation of narratives and haikus is to complete a mutual transformation mechanism between a narrative and a haiku. In this work, the authors propose a framework for transforming a narrative into haiku. The paper shows a basic method of generating haiku from a fragmented narrative by selecting, arranging, and modifying the elements in the narrative. The authors have been developing an Integrated Narrative Generation System (INGS) that automatically generates narratives. The authors aim to introduce the developed haiku-relating mechanism into the INGS in the future.

A Method of Naimaze of Narratives Based on Kabuki Analyses and Propp's Move Techniques for an Automated Narrative Generation System

A Method of Naimaze of Narratives Based on Kabuki Analyses and Propp's Move Techniques for an Automated Narrative Generation System

Analyzing Multiple Narrative Structures of Kabuki based on the Frameworks of Narrative Generation Systems

Although kabuki is a genre of, so to speak, traditional performing arts, it also has many of the characteristics of a contemporary genre, including such various elements as narrative, drama, dance, and music. This analysis and study will contribute to the design and development of studies on digital-narrative generation. The author has previously surveyed and analyzed kabuki’s narrative structures from the viewpoint of a multiple narrative structure model, particularly the generation or production processes involved in its creation and its reception and consumption processes. Kabuki’s multiple-narrative-structure model means that the entire structure of kabuki is constructed through multiple usages of related information. For example, in kabuki the element of the “person” is divided into three: a “character” within a narrative work, an actor with a history of performances and who uses a stage name, and a real human with a true name. This multiplicity provides the person with multiple and deep characteristics. In this paper, based on these previous studies, the author discusses a method that bridges this kabuki analysis with system design and involves the use of two narrative generation systems: an Integrated Narrative Generation System (INGS) and a Geino Information System (GIS).

Informational Narratology and Automated Content Generation

Several studies have proposed a concept called “informational narratology” or “information narratology.” In this paper, we integrate narratological studies, including narratology and various literary theories, into information technologies, such as artificial intelligence and cognitive science, in order to mainly design and develop systems that automatically generate, create, or produce digital narrative contents related to a variety of existing or future narrative genres. Under this framework, we design and develop narrative generation systems, advertise image processing systems, and develop narrative film operation systems. In this paper, we present an overview of the concept of informational narratology, and introduce the above three studies as concrete approaches to its development.

Analyzing Multiple Narrative Structures of Kabuki based on the Frameworks of Narrative Generation Systems

Analyzing Multiple Narrative Structures of Kabuki based on the Frameworks of Narrative Generation Systems

What Happens Next? Event Prediction Using a Compositional Neural Network Model

We address the problem of automatically acquiring knowledge of event sequences from text, with the aim of providing a predictive model for use in narrative generation systems. We present a neural network model that simultaneously learns embeddings for words describing events, a function to compose the embeddings into a representation of the event, and a coherence function to predict the strength of association between two events. We introduce a new development of the narrative cloze evaluation task, better suited to a setting where rich information about events is available. We compare models that learn vector-space representations of the events denoted by verbs in chains centering on a single protagonist. We find that recent work on learning vector-space embeddings to capture word meaning can be effectively applied to this task, including simple incorporation of a verb's arguments in the representation by vector addition. These representations provide a good initialization for learning the richer, compositional model of events with a neural network, vastly outperforming a number of baselines and competitive alternatives.

A Way for using the Verb Conceptual Dictionary in an Integrated Narrative Generation System: the Use of Co-occurrence Information on Verb Concepts

A Way for using the Verb Conceptual Dictionary in an Integrated Narrative Generation System: the Use of Co-occurrence Information on Verb Concepts

A Design Plan of a Game System including an Automatic Narrative Generation Mechanism: The Entire Structure and the World Settings

In this paper, we propose a narrative generation system based on the scenario generation method in tabletop roleplaying games (TRPGs). This system uses an integrated narrative generation system (INGS) that synthesizes various narrative generation mechanisms. The TRPG is an analog game in which one or more players (PLs) play the role of characters within the framework of the narrative prepared by the game master (GM). A PL promotes the development of scenes, which leads to the completion of the narrative. In particular, we concentrate on the “world setting” that consists of the rules or constricts for a narrative and also the components defined by the rules and the stage setting of the narrative. In an ordinary scenario, a GM sets a basic world setting for the narrative generation through the interaction between the PLs. We consider preliminarily prepared scripts corresponding to various world settings in addition to the detailed mechanism to use it.

Automatic Generation, Creativity, and Production of Narrative Content

In accordance with the concept of this organized session, in this presentation, we will consider the study of automatic narrative or story generation as a research field of artificial intelligence (AI) at the levels of generation, creation, and production. Firstly, we study the technologies of narrative or story generation systems based mainly on artificial intelligence and cognitive science. Next, the artistic and aesthetic problems of narrative creation are considered in terms of their relationships with technologies and systems of narrative generation. Further, issues of organizational or social narrative production are presented. The survey and discussion will be conducted based on topics in this session relating to game and advertising systems and our integrated narrative generation system.

A Way for Using the Verb Conceptual Dictionary in an Integrated Narrative Generation System: the Use of Co-occurrence Information on Verb Concepts

A Way for Using the Verb Conceptual Dictionary in an Integrated Narrative Generation System: the Use of Co-occurrence Information on Verb Concepts

共創型物語生成システムに向けて

共創型物語生成システムに向けて

Experimental Development Of A Focalization Mechanism In An Integrated Narrative Generation System

Abstract “Focalization” is a narrative discourse technique that produces different narrative structures based on choosing unique perspectives from which to present a story. This study designs a focalization mechanism and presents an experimental implementation. The proposed system functions as part of our integrated narrative generation system (INGS). In addition, the approach computationally extends the conceptual research of focalization by Genette to techniques for narrative generation. We define focalization as a procedure to transform a story structure into discourse structures through the following two steps: 1) restricting the scope of story information perceived from a chosen perspective, and 2) generating a discourse structure based on perceived story information. In particular, we define two types of rules for restricting the perception scope based on: a) objective perceptible possibility of constituent elements in a story and b) situations or states in which constituent elements in a story are positioned. Based on the experimentally implemented system, we present generated examples from a story using different focalization types. Through analysis, we show that the basic function of the focalization mechanism was achieved by the aforementioned rules.