A structured metadata approach for dealing in an 'intelligent' way with complex 'narrative' information. (15th September 2011)

• Record Type: Journal Article
• Authors: Zarri, Gian Piero
• Is Part Of: International journal of metadata, semantics and ontologies. Volume 6:Number 1(2011)
• Page Start: 10
• Page End: 22
• Publication Date: 2011-09-15
• Subjects: narrative information -- narratology -- artificial intelligence -- structured metadata -- knowledge representation -- ontology of concepts -- ontology of events -- querying and inferencing -- inference engines; Metadata -- Periodicals; Semantic Web -- Periodicals; Ontologies (Information retrieval) -- Periodicals; Data structures (Computer science) -- Periodicals; Information theory -- Periodicals; 005.74
• Languages: English
• ISSNs: 1744-2621

Abstract

In this paper, we evoke first the ubiquity and the importance of the so-called 'non-fictional narrative' information. This consists of streams of logically and chronologically related elementary events that describe the activities or experiences of some (not necessarily human) characters. We show then that the usual knowledge representation and 'ontological' techniques have difficulties in finding complete solutions for representing and using this type of information. After that, we supply some details about Narrative Knowledge Representation Language (NKRL); NKRL is both a representation language – based on the use of 'structured metadata' – and a querying/inferencing environment, which has been expressly created for an 'intelligent' exploitation of (mainly non-fictional) narratives. The paper will be illustrated with some examples concerning recent concrete applications of NKRL.