A Forgetting-based Approach to Merging Knowledge Bases
This work addresses knowledge base merging for AI systems, presenting an incremental improvement with new operators derived from variable forgetting.
The paper tackles the problem of merging multiple knowledge bases by introducing a novel approach based on variable forgetting to resolve contradictions and develop new merging operators, resulting in intuitive variable selection information compared to traditional methods.
This paper presents a novel approach based on variable forgetting, which is a useful tool in resolving contradictory by filtering some given variables, to merging multiple knowledge bases. This paper first builds a relationship between belief merging and variable forgetting by using dilation. Variable forgetting is applied to capture belief merging operation. Finally, some new merging operators are developed by modifying candidate variables to amend the shortage of traditional merging operators. Different from model selection of traditional merging operators, as an alternative approach, variable selection in those new operators could provide intuitive information about an atom variable among whole knowledge bases.