Framework for Designing Questionnaire Using Machine Learning

For a long time, people have been trying to find a way to retrieve information from a large text database. Convert data into information we need. In current search engines, when we search about something rather than giving the precise answer it takes out keywords from our search and gives us documents or web pages related to those words but what we want is the exact answer, why does the user have to search for it. That is, search engines deal more with whole document retrieval. However, a user often wants an exact or specific answer to the question. For instance, given the question "When is Holi festival this year?", what he wants is the answer "March 9, 2022", rather than to read through lots of web pages that contain the words "Holi", "festival", "year", etc. to find the date of the festival. That is, what a user needs is information retrieval, rather than current document retrieval. We handle the task of answering questions, where the answers are in documents in an extensive text database. We take on a machine learning technique to answer questions. In particular, answer candidates are classified and ranked by a classifier trainee donaset of question-answerpairs.