A question answering is a computer science discipline within information retrieval and natural language processing which is concerned with building systems that automatically answer questions asked by humans in a natural language. Question answering system is a software solutions that performs the question answering model. It fetches answers from a large pool of data stored. A Q/A system is generally built to be contextualized to a specific domain like banking, sales, stock market etc.

The project performs similar to the AskMSR model. The architecture of the AskMSR system systematically evaluates contributions of different system components to accuracy. It differs from other question answering system in its dependency on data redundancy rather than sophisticated linguistic analyses of either questions or candidate answers. It is said that a wrong answer is often worse than no answer, in this system we follow the method where a particular reply is given for answers the system does not know.