An RDF-Based Blackboard Architecture for Improving Table Analysis

Table analysis is a complex problem, involving searching solutions from a large search space. Studies show that finding the most credible answers to complex problems often require combining multiple kinds of knowledge. Although the literature shows that both layout and language information have been used in table extraction systems, the amount of information each system uses is limited, and up till now, there is not an easy, systematic way to incorporate new information in these systems. This paper describes a framework for combining multiple solutions (including partial solutions) to solve a general table recognition problem.