Search engines have played a very important role in helping the users to search the necessary information from the huge information. By displaying the list of links to documents.The Question-Answering systems are gaining popularity. Because The main benefit of such QA systems is that the user can ask the query (question) in natural language and he /she get a precise and appropriate answer instead of just displaying a list of links to documents. The main advantage of the proposed Question answering system, which is not restricted to a specific domain. This approach is related to a natural language interface to the database (NLIDB), which takes a natural language query as input and giving the appropriate answer from the manually created knowledge base(structured database). There are two main steps of implementation of the proposed question answering system. The first step is to use a classifier to identify appropriate tables and columns in a structured database for an incoming question, and the second step is to perform the free text retrieval to lookup answer. The system uses named entity normalization, part-of-speech tagging, and a statistical classifier trained on data from the TREC QA task.

No abstract