Baikadi, Alok (North Carolina State University) | Goth, Julius (North Carolina State University) | Mitchell, Christopher M. (North Carolina State University) | Ha, Eun Y. (North Carolina State University) | Mott, Bradford W. (North Carolina State University) | Lester, James C. (North Carolina State University)
The task of narrative visualization has been the subject of increasing interest in recent years. Much like data visualization, narrative visualization offers users an informative and aesthetically pleasing perspective on “storydata.” Automatically creating visual representations ofnarratives poses significant computational challenges due to the complex affective and causal elements, among other things, that must be realized in visualizations. In addition, narratives that are composed by novice writers pose additional challenges due to the disfluencies stemming from ungrammatical text. In this paper, we introduce the NARRATIVE THEATRE, a narrative visualization system under development in our laboratory that generates narrative visualizations from middle school writers’ text. The NARRATIVE THEATRE consists of a rich writing interface, a robust natural language processor, a narrative reasoner, and a storyboard generator. We discuss design issues bearing on narrative visualization, introduce the NARRATIVE THEATRE, and describe narrative corpora that have been collected to study narrative visualization. We conclude with a discussion of a narrative visualization research agenda.
We summarize recent developments in our platform for symbolically representing and reasoning over human narratives. The expressive range of the system is bolstered by the infusion of a large library of knowledge frames, including verbs, adjectives, nouns and adverbs, from external linguistic resources. Extensions to the model itself include alternate timelines (imagined states for goals, plans, beliefs and other modalities), hypotheticals, modifiers and connections between instantiated frames such as causality. We describe a corpus collection experiment that evaluates the usability of the graphical encoding interface, and measure the inter-annotator agreement yielded by our novel representation and tool.
Storytelling and story generation systems usually require knowledge about the story world to be encoded in some form of knowledge representation formalism, a notoriously time-consuming task requiring expertise in storytelling and knowledge engineering. In order to alleviate this authorial bottleneck, in this paper we propose an end-to-end computational narrative system that automatically extracts the necessary domain knowledge from corpus of stories written in natural language and then uses such domain knowledge to generate new stories. Specifically, we employ narrative information extraction techniques that can automatically extract structured representations from stories and feed those representations to an analogy-based story generation system. We present the structures we used to connect two existing computational narrative systems and report our experiments using a dataset of Russian fairy tales. Specifically we look at the perceived quality of the final natural language being generated and how errors in the pipeline affect the output.
Analogy is heavily used in instructional texts. We introduce the concept of analogical dialogue acts (ADAs), which represent the roles utterances play in instructional analogies. We describe a catalog of such acts, based on ideas from structure-mapping theory. We focus on the operations that these acts lead to while understanding instructional texts, using the Structure-Mapping Engine (SME) and dynamic case construction in a computational model. We test this model on a small corpus of instructional analogies expressed in simplified English, which were understood via a semi-automatic natural language system using analogical dialogue acts. The model enabled a system to answer questions after understanding the analogies that it was not able to answer without them.
The telling and understanding of stories is a universal part of human experience. If we could reproduce even part of the process inside a computer, it could expand the possibilities for human-computer interaction enormously. We argue that in order to do so, we need to model narrative at three levels of abstraction, in terms of physics, characters and plot. Taking four scenes from the children's story The Tale of Peter Rabbit, we describe some of the challenges they present for modeling this kind of "story-sense reasoning".