Abstract: Question Answering (QA) is a computer science discipline within the fields of information retrieval and natural language processing, which is used to build systems that automatically answer questions posed by humans in a natural language. The system propose learning to paraphrase for question answering, Here turns to Paraphrases as a means of capturing this knowledge and present a general framework which learns different paraphrases for various QA tasks. Our method is trained different question-answer pairs. A question and its paraphrases input to a neural scoring model which assigns higher weights to each expressions most likely to yield correct answers. Here discuss about different paraphrase generation methods and check the generated paraphrase sentence with a scoring model. The advantages and limitations of these methodologies are also discussed.

Keywords: Question Answering (QA), Natural Language Processing (NLP), Paraphrase generation, Paraphrase Scoring Model Question Answering Model