Natural Language Processing based Text Summarization and Querying Model

Learning skills play a very important role to build a student’s foundation for a language. It becomes difficult for students to analyze the important information available in an extensively lengthy passage. Our proposed system focuses on helping students in developing their skills by understanding passages in their textbooks through text summarization and question-answer module. The main idea is to save a potential amount of time and effort of readers in finding valuable information in a given document. Also, the question and answer extraction help one to understand a passage in much depth. Our model primarily focuses on History Textbooks passages of Secondary School Certificate (SSC) Board Maharashtra State that consists of facts and figures by combining the Text Summarization Module with Question Answer Module. To achieve this task of text summarization we used the Term Frequency Inverse Document Frequency (TF-IDF) algorithm and question answers are generated based on the generated summary with the help of Stanford CoreNLP suite.