Computational story generation

Date: 
Wednesday, September 16, 2015 - 15:00 - 16:30
Location: 
Building R Annexe
Presenter: 
Tony Veale & Pablo Gervás

We are very pleased to invite you to the next CLiPS Colloquium.

On September 16, Prof. Tony Veale and Prof. Pablo Gervás will introduce the topic of computational story generation. Below you can find more detailed information about the content of each talk and about the two speakers. We are looking forward to welcome you on this occasion, sure that it will be an amazing opportunity to come into contact with an interesting research field and two of the most important scholars who are promoting computational creativity among the research communities interested in natural language processing and generation.



Telling Stories By Putting Narrative Substance on Image Schemas

Prof. Tony Veale, School of Computer Science and Informatics, University College Dublin

 

ABSTRACT – What is a hero without a quest? And what is a quest that does not transform its hero in profound ways? The scholar Joseph Campbell has argued that our most steadfast myths persist because they each instantiate, in their own way, a profoundly affecting narrative structure that Campbell calls the monomyth. Campbell sees the monomyth as a productive schema for the generation of heroic stories that, at their root, follow the image-schematic pattern of a journey either literally or figuratively. Many ancient tales subconsciously instantiate this journey schema, while many modern stories – such as George Lucas’s Star Wars – are consciously written so as to employ Campbell’s monomyth schema as a narrative deep-structure. So Campbell’s monomyth (and, indeed, the folkloristic morphology of Vladimir Propp) can be subsumed under a more abstract, yet ultimately experientially-grounded, mental structure called the Source-Path-Goal (SPG) schema.

Cognitive linguists argue that any purposeful action along a path – from going to the shops to undertaking a quest – activates an instance of the SPG schema in the mind. But the SPG is just one of the pervasive image schemas in human thought that shape our understanding of human experiences and the stories we tell about them. Other spatially-grounded schemas, such as vertical movement, connection/disconnection and containment, are freighted with narrative potential. In this talk I explore computational ways of converting this potential into working story-telling code.

BIO – Tony Veale is a senior lecturer in the department of Computer Science at University College Dublin (UCD), Ireland. He has been a researcher in the areas of Computational Linguistics, Cognitive Science, Cognitive Linguistics and Artificial Intelligence since 1988, both in industry and in academia. He obtained a B.Sc (hons) in Computer Science from University College Cork (UCC) in 1988, and an M.Sc in Computer Science in 1990, before joining Hitachi Dublin Laboratory in 1990. He received his Ph.D in Computer Science from Trinity College, Dublin in 1996. He has divided his career between academia and industry. In the latter, he has developed text-understanding and machine translation systems (in particular, the translation of English into American Sign Language, ASL), as well as natural-language-processing tools, and patented web-based question-answering technology. He was, from 2002–2007, the academic coordinator for UCD's unique international degree programme in Software Engineering, which UCD delivers in Shanghai at Fudan university; he continues to deliver courses on this degree. He is the author of Exploding The Creativity Myth: The Computational Foundations of Linguistic Creativity (Bloomsbury Academic, 2012) and a founder member of the international Association for Computational Creativity (ACC). He is the coordinator of PROSECCO - PROmoting the Scientific Exploration of Computational Creativy (http://prosecco-network.eu), a 3-year coordination action involving 7 universities from 6 countries, whose goal is to foster research about computational creativity, a discipline exploring the capabilities of computers to perform tasks that would be considered creative by unbiased human observers.

 


In Search of Appropriate Abstractions for the Computational Synthesis of Narrative

Prof. Pablo Gervás, Facultad de Informática, Universidad Complutense de Madrid


ABSTRACT – The synthesis of narrative, whether to capture the essence of an existing narrative or to generate a draft for a new one, requires an appropriate vocabulary of representational elements. Because narrative is presented to us in many forms – text, speech, pictures, film – the shared essence of this narrative must be something that can be abstracted from all these different forms, and which we aim to represent conceptually if we want to manage it computationally. There have been a number of attempts to formulate representations of this type in literary studies, but usually not very rigorous in their computational approach – mostly because they were only intended as descriptive or explanatory formalisations rather than generative ones.

My talk will focus on recent work at UCM, in the context of the WHIM project, to review some of these existing attempts and to distill from them a set of abstractions suitable to represent the essence of narratives in a way that can work both to represent existing narratives and to generate drafts for new ones. The approaches reviewed range from Propp's Morphology of the Folk Tale and Polti`s Thirty Six Dramatic Situations to Booker's Seven Basic Plots. The abstractions that have been found most relevant concern an elementary unit of plot, much in the vein of Propp's character functions, a set of narrative roles played by characters, and a set of long-range dependencies between elements in a plot. Based on abstractions such as these, a generative procedure has been proposed that, when provided with the necessary knowledge resources tailored to a particular domain, allows construction of acceptable narratives.

BIO – Pablo Gervás works as associate professor (profesor titular de universidad) at the Departamento de Ingeniería del Software e Inteligencia Artificial, Facultad de Informática, Universidad Complutense de Madrid. He is the director of the NIL research group (http://nil.fdi.ucm.es) and also of the Instituto de Tecnología del Conocimiento (http://www.itc.ucm.es). In recent years, Gervás has taken part in the organization of several scientific meetings on topics related to creativity. He was founding member of the Computational Creativity Working Group (WG4) of initiative COST 282: “Knowledge Discovery in Science and Technology,” funded by the European Commission. His research is on computational creativity, processing natural language input, generating natural language output, building resources for related tasks, and generating stories. In the area of creative text generation, he has done work on automatically generating metaphors, formal poetry, fairy tales, and short films. He is now involved in the following projects related to computational creativity: "WHIM: The What If Machine" (http://www.whim-project.eu/) and "ConCreTe: Concept Creation Technologies" (http://conceptcreationtechnology.eu/), and he is also involved in the PROSECCO initiative.

 

Signups closed for this CLiPS Colloquium