Abstract
In this paper, we evoke first the ubiquity and the importance of the so-called ‘non-fictional narrative’ information, with a particular emphasis on the terrorism- and crime-related data. We show that the usual knowledge representation and ‘ontological’ techniques have difficulties in finding complete solutions for representing and using this type of information. We supply then some details about NKRL, a representation and inferencing environment especially created for an ‘intelligent’ exploitation of narrative information. This description will be integrated with concrete examples to illustrate the use of this conceptual tool in a terrorism context.
TopIntroduction
‘Narrative’ information concerns the account of some real-life or fictional story (a ‘narrative’) involving concrete or imaginary ‘personages’. In this paper, we will deal with those (multimedia) non-fictional narratives that are typically embodied into corporate memory documents (memos, policy statements, reports, minutes, documentation archives for product development…), news stories, normative and legal texts, medical (or financial, cadastral, administrative…) records, audit reports, many intelligence messages, surveillance videos or visitor logs, actuality photos and video fragments for newspapers and magazines, eLearning and Cultural Heritage material (text, image, video, sound…), plotting and narrative course of actions for videogames, etc.
Note, in particular, that dealing with non-fictional narrative material is of paramount importance for analysis and management of any sort of crisis situation and, more in general, for enhancing the ability to fight terrorism and other crimes. For example, six critical mission areas have been identified in the “National Strategy for Homeland Security” report (2002). Of these, at least two, “Intelligence and Warning” and “Domestic Counter-terrorism” are based on the processing of non-fictional narrative information in order, e.g., to “… find cooperative relationships between criminals and their interactive patterns”. Managing non-fictional narrative information must then be considered as an essential component of the emerging science of “Intelligence and Security Informatics” (ISI), as defined, e.g., in (Chen and Wang, 2005; Chen, 2006).
From a concrete point of view, ‘non-fictional narratives’ deal with the description of spatially and temporally characterized ‘events’ that relate, at some level of abstraction, the behavior or the state of given real-life ‘actors’ (characters, personages, etc.): these try to attain a specific result, experience particular situations, manipulate some (concrete or abstract) materials, send or receive messages, buy, sell, deliver etc. Note that:
- •
The term ‘event’ is taken here in its most general meaning, covering also strictly related notions like fact, action, state, situation, episode, activity etc.
- •
The ‘actors’ or ‘personages’ involved in the events are not necessarily human beings: we can have narratives concerning, e.g., the vicissitudes in the journey of a nuclear submarine (the ‘actor’, ‘subject’ or ‘personage’), the various avatars in the life of a commercial product, or the description of an industrial equipment that passes from an ‘idle’ to a ‘working’ state.
- •
Even if a large amount of non-fictional narratives are embodied within natural language (NL) texts, this is not necessarily true: narrative information is really ‘multimedia’. A photo representing a situation that, verbalized, could be expressed as “The US President is addressing the Congress” is not of course an NL document, yet it surely represents a narrative.
In this paper, we will present an Artificial Intelligence tool, NKRL, “Narrative Knowledge Representation Language”, see (Zarri, 2003; 2005a; 2009) that is, at the same time:
- •
a knowledge representation system for describing in some detail the essential content (the ‘meaning’) of complex non-fictional narratives;
- •
a system of reasoning (inference) procedures that, thanks to the richness of the representation system, is able to automatically establish ‘interesting’ relationships among the represented data;
- •
an implemented software environment.
Key Terms in this Chapter
Narrative Documents or ‘Narratives’: Multimedia documents like memos, policy statements, reports, minutes, news stories, normative and legal texts, eLearning and Cultural Heritage material (text, image, video, sound…), etc. In these ‘narratives’, the main part of the information content consists in the description of ‘events’ that relate the real or intended behaviour of some ‘actors’ (characters, personages, etc.): these try to attain a specific result, experience particular situations, manipulate some (concrete or abstract) materials, send or receive messages, buy, sell, deliver etc.
NKRL Inference Engine: Software modules that carry out the different ‘reasoning steps’ included in the NKRL inference rules, ‘hypotheses’ or ‘transformations’. It allows us to use these two classes of inference rules also in an ‘integrated’ mode, augmenting then the possibility of finding interesting (implicit) information.
NKRL Inference Rules, Transformations: These rules try to ‘adapt’, from a semantic point of view, a query that failed to the contents of the existing knowledge bases. The principle employed consists in using rules to automatically ‘transform’ the original query into one or more different queries that are not strictly ‘equivalent’ but only ‘semantically close’ to the original one.
‘Binary’ Languages vs. n-ary Languages: Binary languages (like RDF and OWL) are based on the classical ‘attribute – value’ model: they are called ‘binary’ because, for them, a property can only be a binary relationship, linking two individuals or an individual and a value. They cannot be used to represent in an accurate way the narratives that require, in general, the use of n-ary knowledge representation languages.
Predicative Occurrences: In NKRL, these are conceptual structures obtained from the instantiation of templates and used to represent particular elementary events.
Templates: In NKRL, templates take the form of combinations of quadruples connecting together the ‘symbolic name’ of the template, a ‘predicate’ – as BEHAVE, MOVE, OWN, PRODUCE… – and the ‘arguments’ of the predicate (concepts or combinations of concepts) introduced by named relations, the ‘roles’ (like SUBJ(ect), OBJ(ect), SOURCE, BEN(e)F(iciary), etc.). The quadruples have in common the ‘name’ and ‘predicate’ components. If we denote then with Li the generic symbolic label identifying a given template, with Pj the predicate used in the template, with Rk the generic role and with ak the corresponding argument, the NKRL core data structure for templates has the following general format (Li (Pj (R1 a1) (R2 a2) … (Rn an))). Templates are included in an inheritance hierarchy, HTemp(lates), which implements NKRL’s ‘ontology of events’.
NKRL Inference Rules, Hypotheses: They are used to build up automatically ‘reasonable’ connections among the information stored in an NKRL knowledge base according to a number of pre-defined reasoning schemata, e.g., ‘causal’ schemata’.
Connectivity Phenomena: A term drawn from Computational Linguistics: in the presence of several, logically linked elementary events, it denotes the existence of a global information content that goes beyond the simple addition of the information conveyed by the single events. The connectivity phenomena are linked with the presence of logico-semantic relationships like causality, goal, indirect speech, co-ordination and subordination etc., as in a sequence like: “Company X has sold its subsidiary Y to Z because the profits of Y have fallen dangerously these last years due to a lack of investments”. These phenomena cannot be managed by the usual ontological tools; in NKRL, they are dealt with using second order tools based on reification.
NKRL: The Narrative Knowledge Representation Language. ‘Classical’ ontologies are largely sufficient to provide a static, a priori definition of the concepts and of their properties. This is no more true when we consider the dynamic behaviour of the concepts, i.e., we want to describe their mutual relationships when they take part in some concrete action, situation etc. (‘events’). NKRL deals with this problem by adding to the usual ontology of concept an ‘ontology of events’, a new sort of hierarchical organization where the nodes, called ‘templates’, represent general classes of events like “move a physical object”, “be present in a place”, “produce a service”, “send/receive a message”, etc.
Binding Occurrences: Second order structures used to deal with those ‘connectivity phenomena’ (see above) that arise when several elementary events are connected through causality, goal, indirect speech etc. links. They consist of lists of symbolic labels (ci) of predicative occurrences; the lists are differentiated using specific binding operators like GOAL, CONDITION and CAUSE.