Searching For Conceptual Connectivity Among A S37 Of Concepts
S. Bandyopadhyay, S. Arunkumar · 2005
It has been argued that adequate theories of memory and the structure of knowledge largely eliminates the need for a theory of inference. In this formulation what gets inferred is a function of what gets accessed in memory. Thus, the structure and the behaviour of the memory organization needs more attention. The knowledge is viewed in terms of a set of linked concepts in memory. So the key question in this context is, how can a large set of concepts in a memory be organized so that relevant concepts can be searched and linked efficiently? This paper proposes a memory organization and describes a mechanism of finding out the correct association among a set of Input concepts. It implements an active search technique to find out the connectivity among input concepts by bridging sequences of concepts. It aims to resolve the word sense ambiguity problem by selecting the correct sense of a word in a given context, The organization centers upon a model based on a modified theory of spreading activation and proposes a notion of concepts flow, originated from dataflow model of computation to implement an active search technique In a computer. The spreading of activation in a concept flow graph is viewed as propagation of concept tokens from one concept node to another until a connectivity is detected.