A COMPARATIVE COST ANALYSIS OF TEXT BASED ON CLUSTERING AND ENTROPY MODEL

摘要

The World Wide Web is very large and fast growing source of information now days. Lot of this information is in the unstructured form of text which makes user hard to extract the information by query. To make the queries easy and to improve accuracy of result, template extraction technique is used .In the existing system the techniques which are used to extract the data are not efficient and causes the factors such as delay. The proposed system is presented with MDL Principle. System extracts the templates from a large number of web documents which are generated from heterogeneous templates. This helps web application like web search to improve performance. In addition the proposed technique makes use of a clustering technique to retrieve the web documents based on the similarity of underlying template structures in the documents. So the template for each cluster is extracted simultaneously with its fast approximation of clustering.