An Integrated Framework for Technical Document Summarization and Multiple-Choice Question Generation

Exams and assessments are going through a significant shift nowadays. The bulk of assessments are switching to MCQ-based objective tests, which are time-consuming to develop and need to administer daily. It is becoming increasingly important to have an automated MCQ generation system that is cost- as well as time-effective. Another pressing issue arose with the rapid growth of the internet is information overloading which demands systems for summarization. There are many studies being done on text summarization. As a result of the growth of online information these days, these investigations are gaining more and more popularity especially among academics as it simplifies a large text without missing the relevant information. Here we are putting up an integrated framework for summarizing a large academic technical document and for generating Multiple Choice Questions from it. The framework employs extractive text summarization and natural language processing techniques. The intention is to extract vital information from the technical documents. Automating the development of questions using AIpowered technologies is a time- and money-effective methodology that reduces the requirement for human engagement as compared to the traditional form-based method for MCQ generation. In the paper setting, a significant amount of time is saved for both summarization and MCQ generation.