Kalyani Charitable Trust’s

Late G. N. Sapkal College of Engineering

Sapkal Knowledge Hub, Kalyani Hills, Anjaneri, Trimbakeshwar Road,
Nashik – 422 212, Maharashtra State, India

Department:-Electronics and Telecommunication Engineering

B.E E&T.C Project:-[2024-25]

Synopsis

Name of Topic:- “Automatic Question Generation Using NLP”

Sr.No Name of Student Email-ID Contact.No

1 Khairnar Om Sudhir omkhairnar84@gmail.com 7875295727

2 Bhosle Pratik Bhagvat pratikbhosale9909@gmail.com 9730738953
3 Pawar Deepak Arjun deepakpawar2752002@gmail.com 9359727549

Area of project:- “Artificial Intelligence”

 Scope of the Project

The generation of questions from text is useful in numerous application domains, but manual generation is
time-consuming and costly. In addition to being a web-based anddesktop-based application system, it offers
several features mainly for producing MCQs, Boolean type, and fill-in-the-blank questions. The goal of this
application is to describe anautomatic question generator built on NLP.
This system helps students to self analyze theirknowledge about the subject. The application can be used in
the educational field, and it ishelpful in generating test papers for assessment. The generated questions are
displayed onthe student side with questions and answers and like an assessment for practice test for students.
It is helpful in competitive exams by generating questions and practicing them.
This project can be further extended to generate paraphrasing questions, descriptive questions, and question
paper generation for different types of questions. It is also possibleto add additional automated answer copy-
checking systems to verify the answers and provide the results to the students.
 Abstract

This project introduces an innovative approach to advance the field of automatic question generation using
natural language processing (NLP), with a specific focus on Bloom’s Taxonomy. With the increasing
availability of resources and on-line learning platforms there is a need for efficient methods to create diverse
andcontextually relevant questions. The main goal of this project is to develop a system that can
automatically generate questions using Natural Language Processing(NLP) techniques aligned with first three
cognitive levels of Bloom’s Taxonomy: remembering, understanding, and applying. This project will make a
contribution to the field of NLP by providing a framework for automatic question generation. The project
follows stages; preprocessing the input text identifying concepts and information creating question rules and
generating different versions of questions basedon these rules. This project utilizes NLP techniques such as
Named Entity Recognition (NER) Part of Speech tagging (POS), syntatic analysis and Discourse analysis.
The overarching goal is to provide educators, content creators, and learners with an efficient and intelligent
tool for generating questions that enhance comprehension and critical thinking. By automating this process,
the project seeks to save time and effort while improving the overall learning and assessment experience.

Keywords: Automatic Question Generation, Bloom’s Taxonomy, Natural Language Processing, Quality
Assessment, Learning Assessment, Compherension, NER, POS tagging
 Introduction

This project introduces an innovative approach to advance the field of automatic question generation using
natural language processing (NLP), with a specific focus on Bloom’s Taxonomy. With the increasing
availability of resources and online learning platforms there is a need for efficient methods to create diverse
and contextually relevant questions. The main goal of this project is to develop a system that can
automatically generate questions using Natural Language Processing (NLP) techniques aligned with first
three cognitive levels of Bloom’s Taxonomy: remembering, understanding, and applying. This project will
make a contribution to the field of NLP by providing a framework for automatic question generation. The
project follows stages; preprocessing the input text identifying concepts and information creating question
rules and generating different versions of questions based on these rules. This project utilizes NLP
techniques such as Named Entity Recognition (NER) Part of Speech tagging (POS), syntatic analysis and
Discourse analysis. The overarching goal is to provide educators, content creators, and learners with an
efficient and intelligent tool for generating questions that enhance comprehension and critical thinking. By
automating this process, the project seeks to save time and effort while improving the overall learning and
assessment experience.
 Block Diagram

Fig. Block Diagram of System

Flowchart

Fig. Flowchart
 Software’s-Hardware Required

1. Operating System: Windows 7 or above.

2. Libraries: NLTK, Spacy, Stanford NLP, Stanza etc.
3. Programming Language: Python.
4. IDE: Visual Studio Code, Jupyter Notebook.
5. CPU: 4 or more cores.
6. RAM: 8 GB or more.
7. Hard Disk Drive: 500 GB/1TB.
 Advantages

 AQG can save time and effort by automating the process of generating question papers.
 AQG can help ensure that questions are well-structured, varied, and aligned with learning
outcomes.
 AQG can help reduce the risk of paper leakage because the admin has control
over the system.
 AQG can adapt to the needs of individual learners, allowing for a more personalized
learning experience.
 AQG can help chatbots generate interesting questions and identify user needs.
 Applications

 Chatbots: NLP can help chatbots generate interesting questions to better serve customers.
 Education: NLP can help educators quickly generate question papers and assess student
performance.
 Text summarization: NLP can be used to generate questions and summarize text.

References

 D. R. Ch and S. K. Saha, “Automatic Multiple Choice Question Generation from Text: A

Survey,” IEEE Transactions on Learning Technologies, vol. 13, no. 1. Institute of Electrical
and Electronics Engineers, pp. 14–25, Jan. 01, 2020. doi: 10.1109/TLT.2018.2889100.Atmel
AVR Microcontroller Primer: Programming and Interfacing By: Steven F. Barret, Daniel J.Pack.

 Ankita and K. A. Abdul Nazeer, “Part-of-speech tagging and named entity recognition using improved
hidden markov model and bloom filter,” in 2018International Conference on Computing, Power and
Communication Technologies,GUCON 2018, Mar. 2019, pp. 1072–1077. doi: 10.1109/GUCON.RK
Mittal and IJ Nagarath “Robotics and Control” BITS Pilani, 2003

 https://www.researchgate.net/publication/369228453_Automatic_Question_Generator_Using_Natural_
Language_Processing .

 http://android.com

Prof.S.G.Bagul Prof.S.B.Borse
B.E Project Coordinator Project Guide & Head of Department