Since McCarthy`s Turing Award speech, in 1971, the notion of context has been used in Artificial Intelligence to localize reasoning, in the sense that intelligent agents reasoning depends on the situation agents are embedded in, and on their cognitive state. A typical example is McCarthy`s above theory, in which, depending on context, the `same` theory, describing a blocks world, can be represented in two different ways with a different degree of generality. The emphasis on the role of context in localizing reasoning does not mean that there is no relation between reasoning performed in different contexts. In many applications of contexts, e.g. reasoning about beliefs, reasoning about viewpoints, integration of heterogeneous information, and multiagent systems, reasoning may involve many interacting contexts. Therefore a certain form of compatibility must exist between facts described in different contexts. This thesis aims at defining a semantics for contextual reasoning, called Local Models Semantics, that formalizes the role of context in localizing reasoning and the relations (compatibilities) among different contexts. Additionally we use tis semantics to formalize two relevant applications, that is, reasoning about beliefs and the integration of heterogeneous information in a federated database. By developing the theory of Local Models Semantics we pursue two objectives. First we aim to illustrate the intuitions underlying the use of context in reasoning. In addition we define a formal semantics for contextual reasoning which formalizes these intuitions. These objectives are accomplished by giving the basic definitions of model, satisfiability, and logical consequence. By applying Local Models Semantics to reasoning about beliefs we intend to provide evidence that our semantics provides enough modularity and flexibility to formalize agents with various introspective reasoning capabilities. Finally, by applying Local Models Semantics to the integration of information coming from heterogeneous databases, we intend to show that a precise formal semantics of a federation of databases can be defined by considering each database in the federation as a context and interactions between different databases as relations between contexts
A Semantics for Contextual Reasoning: Theory and Two Relevant Applications
Ghidini, Chiara
1998-01-01
Abstract
Since McCarthy`s Turing Award speech, in 1971, the notion of context has been used in Artificial Intelligence to localize reasoning, in the sense that intelligent agents reasoning depends on the situation agents are embedded in, and on their cognitive state. A typical example is McCarthy`s above theory, in which, depending on context, the `same` theory, describing a blocks world, can be represented in two different ways with a different degree of generality. The emphasis on the role of context in localizing reasoning does not mean that there is no relation between reasoning performed in different contexts. In many applications of contexts, e.g. reasoning about beliefs, reasoning about viewpoints, integration of heterogeneous information, and multiagent systems, reasoning may involve many interacting contexts. Therefore a certain form of compatibility must exist between facts described in different contexts. This thesis aims at defining a semantics for contextual reasoning, called Local Models Semantics, that formalizes the role of context in localizing reasoning and the relations (compatibilities) among different contexts. Additionally we use tis semantics to formalize two relevant applications, that is, reasoning about beliefs and the integration of heterogeneous information in a federated database. By developing the theory of Local Models Semantics we pursue two objectives. First we aim to illustrate the intuitions underlying the use of context in reasoning. In addition we define a formal semantics for contextual reasoning which formalizes these intuitions. These objectives are accomplished by giving the basic definitions of model, satisfiability, and logical consequence. By applying Local Models Semantics to reasoning about beliefs we intend to provide evidence that our semantics provides enough modularity and flexibility to formalize agents with various introspective reasoning capabilities. Finally, by applying Local Models Semantics to the integration of information coming from heterogeneous databases, we intend to show that a precise formal semantics of a federation of databases can be defined by considering each database in the federation as a context and interactions between different databases as relations between contextsI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
