Automatic question-answer pairs generation and question similarity mechanism in question answering system

Abstract With the swift growth of information over past few years, taking full benefit is increasingly essential. Question Answering System one promising methods to access this much information. The lacks humans’ common sense and reasoning power cannot identify unanswerable questions irrelevant questions. These are answered by making unreliable incorrect guesses. In paper, we address limitation proposing a Similarity mechanism. Before question posed Question-Answering system, it compared with possible generated given paragraph, then Score generated. mechanism effectively identifies proposed incorporates human way This can avoid altogether from being system. It helps Systems focus only on answerable improve their performance. Along this, introduce an application that generates question-answer pairs passage useful in several fields.