VisualRDR: A general framework for creating, maintaining and learning of ripple down rules for Information Extraction

The problem facing the industry and the common user today is that of an information glut. Large amounts of useful information, in various forms, are being generated mostly for human consumption. This deluge of information requires us to find ways of gathering information from such unstructured sources with as little manual intervention as possible. This has been made possible by information extraction. In this paper we propose a novel knowledge-based approach to information extraction. We demonstrate how this knowledge for information extraction can be accrued in an incremental fashion.