Framework for interrogative knowledge identification.

Abstract

The difficulty of defining and capitalizing the knowledge in an organization from the business data captured in text files. These text files defined as unstructured document that is without a specific format example, plain text. Hence, this paper presents an Interrogative Knowledge Identification framework to identify unstructured documents that encompassed knowledge, information, and data. It tries to identify some high-level problems of the area from a higher perspective and then propose a possible solution thru the description of the framework. This research is an experimental approach using an appropriate test collection of unstructured documents. A system was developed based on the Interrogative Knowledge Identification framework. The results obtained are measured in terms of percentage of quantitative retrieval performance recall and precision metrics compared with an expert. This is to improve better understanding the process of making sense the information or knowledge residing in unstructured documents.