Facilitating Document Annotation for Efficient user Relevant Search

摘要

Document Annotation is the process of the addition of metadata information which is very important to fetch the information from the specific document. Due to the increasing sizes of data, it becomes cumbersome for anyone seeking for the information needs to provide assistance of automated approach to find what they are searching for. Clustering is a very important process to extract information from unstructured data, and enhance the process of grouping similar items together. Clustering also helps to discover hidden information and summarize a large amount of data into a small number of groups. We present an approach which maintain domain specific dictionary that helps to generate structured information by recognizing the documents. which contain target specific information. This information is going to be useful for following process of querying database. To the input documents text pre-processing was initially done to extract the terms from the sentences and K-mean algorithm is used for clustering the documents. The goal of the system is to maximize the number of relevant documents in the ranked list as well as making sure that they are high up in the ranked list.