Building an Ontology of Creativity: a language processing approach
Anna Jordanous, King's College London
Bill Keller, University of Sussex
Tuesday 28 February, 6.15pm, Anatomy Museum. Followed by drinks
Register to attend at: http://www.eventbrite.com/event/2658490617
Do you tweet? Please use hashtag #cerchseminars
Abstract
Creativity is a complex and multi-dimensional concept that encompasses many related aspects, abilities, properties and behaviours and can be viewed from many different perspectives. Difficulties in identifying a comprehensive, widely-accepted definition of creativity have hindered progress in computational creativity research as researchers have no baseline to evaluate against or standards to aim towards. An important, related issue is that of defining creativity in a machine-readable format, such that a computational creativity system has a sufficient understanding of the concept to permit self-evaluation. This paper presents an ontology of creativity and its publication as Linked Data within the Semantic Web. Using techniques from statistical natural language processing, we analysed discussions of creativity and identified fourteen distinct themes or components. The components provide an ontology of creativity: a set of building blocks that collectively define creativity. This ontological definition of creativity makes the concept more tractable to study and evaluate, both for humans and machines.
A bout the speakers
Anna Jordanous trained as a computer scientist and has an MSc in Artificial Intelligence from Edinburgh University. Her PhD work proposes and applies a methodological tool to evaluate the creativity of computational creativity systems: SPECS (Standardised Procedure for Evaluating Creative Systems). Anna has also published research in in computational creativity, music information retrieval and computational linguistics, and has been involved in research projects on applying technology in educational contexts. She joined the Centre for e-Research in August 2011 as a post-doctoral researcher on the Sharing Ancient Wisdoms (SAWS) project.
Bill Keller is a Senior lecturer in Computer Science and Artificial Intelligence in the Department of Informatics at the University of Sussex. He has a background in computational linguistics and has published on a wide range of topics in natural language processing, including logical approaches to natural language semantics, formalisms for linguistic knowledge representation, statistical approaches to machine learning of language and distributional accounts of meaning. His current research interests include graph-based methods for word sense discovery and concept extraction and approaches to phrasal similarity and paraphrase.