Document Annotation with Caption Generating

Collections of huge, large textual data contains significant amount of structured information, which remains hidden in unstructured text. Relevant information is always difficult to find in these documents. In this paper we proposed an alternative approach that facilitates the generation of the structured metadata by identifying documents that are likely to contain information of interest and this information is going to be useful for querying the database. Here people will likely to assign metadata related to documents which they upload which will easily help the users in retrieving the documents. In this paper, a method of sentence generation from a given text. The task of sentence generation has its usage in text summarization. The technique that we have applied is N-gram language model.