Adding Context to Concept Trees
This work addresses the challenge of bridging neural architectures and information systems for better semantic networks, though it appears incremental in extending existing models.
The paper tackles the problem of enriching Concept Trees with consistent context to improve knowledge representation and querying, demonstrating through tests that the tree structure is inherent in natural language and enabling enhanced query processes.
A Concept Tree is a structure for storing knowledge where the trees are stored in a database called a Concept Base. It sits between the highly distributed neural architectures and the distributed information systems, with the intention of bringing brain-like and computer systems closer together. Concept Trees can grow from the semi-structured sources when consistent sequences of concepts are presented. Each tree ideally represents a single cohesive concept and the trees can link with each other for navigation and semantic purposes. The trees are therefore also a type of semantic network and would benefit from having a consistent level of context for each node. A consistent build process is managed through a 'counting rule' and some other rules that can normalise the database structure. This restricted structure can then be complimented and enriched by the more dynamic context. It is also suggested to use the linking structure of the licas system [15] as a basis for the context links, where the mathematical model is extended further to define this. A number of tests have demonstrated the soundness of the architecture. Building the trees from text documents shows that the tree structure could be inherent in natural language. Then, two types of query language are described. Both of these can perform consistent query processes to return knowledge to the user and even enhance the query with new knowledge. This is supported even further with direct comparisons to a cognitive model, also being developed by the author.