NLP Based Question Answering System

The proliferation of data in various domains has increased the significance of Question Answering Systems (QAS), which utilize Natural Language Processing (NLP) techniques to comprehend and respond to natural language queries. This review paper provides a comprehensive overview of recent advancements in QAS that employ NLP techniques. However, this thesis concentrates on specific QA scenarios where the answer is explicitly present in the text source. The objective is to build a QA system that can extract answers from plain text sources quickly, precisely, and accurately, using only a single sentence or a fragment of a sentence. The paper discusses the obstacles involved in creating QAS and how NLP techniques can overcome them. The paper proposes a question answering system that combines extractive and abstractive summarization methods to produce brief and accurate answers to user questions. The system uses keyword extraction and classification to identify pertinent information from a collection of documents and then combines extractive and abstractive summarization approaches to create a comprehensive and concise response. The research findings indicate that the proposed system has significant potential to enhance the effectiveness and efficiency of question answering systems in a range of applications.