Home / Current Issue / Paper 1705562
A Survey on Development Approaches for Automated MCQ Generator Using Natural Language Processing
Subject area: Science,Engineering and Technology · Area of research: Machine Learning
Abstract
Within the field of education, it is widely acknowledged that posing questions to learners at the end of a lesson is an effective teaching strategy. For cost-saving reasons, especially when there are multiple candidates, the majority of educational institutions and have made multiple-choice questioning (MCQ) the mainstay of their testing procedures. In Natural Language Processing (NLP), the task of autonomously generating multiple-choice questions is both beneficial and challenging. It involves using textual information to automatically generate relevant and accurate queries. Teachers find it stressful and challenging to manually generate meaningful, significant, and relevant questions, despite its importance. In our project, we describe an NLP-based method for producing MCQs on its own. Natural language processing (NLP) is an artificial intelligence field that studies how humans and computers interact with natural language. Our approach places a strong emphasis on using natural language processing (NLP) to set up multiple choice questions (MCQs). This improves the process of creating and modifying MCQs and creates a useful question bank that academics can use later on with their students. This will ensure that the multiple-choice questions (MCQ) contain options and questions relevant to the learning objectives.
Keywords
Multiple Choice Questions, Natural Language Processing, Distractor Generation, Summary Generation, Automated Question Generation
References
[1] Ruslan Mitkov, Leanha and Nikioskar Amanis. "A computer-aided environment for generating multiple-choice test items.", Research Group in Computational Linguistics, School of Humanities, Languages and Social Sciences, University of Wolverhampton, Wolverhampton WV1 1SB, UK, 2006.
[2] Itziar Aldabe and Montse Maritxalar. "Semantic Similarity Measures for the Generation of Science Tests in Basque.", 2014.
[3] Maha Al-Yahya. "Ontology-Based Multiple Choice Question Generation.", Information Technology Department, 2014.
[4] Manish Agrawal, Prashanth Mannem. "Automatic gap-fill question generation from textbooks.", 2011.
[5] Susanti, Y., Tokunaga, T., Nishikawa, H., and Obari, H., "Automatic distractor generation for multiple Choice English vocabulary questions.", Research and Practice in Technology Enhanced Learning, 2018.
[6] Nwafor, Chidinma Onyenwe, Ikechukwu. "An Automated Multiple-Choice Question Generation using Natural Language Processing Techniques." International Journal on Natural Language Computing, 2021.
[7] Ayako Hoshino and Hiroshi Nakagawa. "A real-time multiple-choice question generation for language testing: A preliminary study." EdAppsNLP 05: Proceedings of the second workshop on Building Educational Applications Using NLP, 2005.
[8] Husam Ali, Ylli as Chali, Sadid A. Hasan. "Automatic Question Generation from Sentences.", 2010.
How to cite this paper
@article{1705562,
author = {Aditya Sangwai, Aditya Agrawal, Prasad Patil, Mandar Kulkarni, Dr. Anupama Phakatkar},
title = {A Survey on Development Approaches for Automated MCQ Generator Using Natural Language Processing},
journal = {Iconic Research And Engineering Journals},
year = {2024},
volume = {7},
number = {9},
pages = {1-5},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1705562.pdf},
abstract = {Within the field of education, it is widely acknowledged that posing questions to learners at the end of a lesson is an effective teaching strategy. For cost-saving reasons, especially when there are multiple candidates, the majority of educational institutions and have made multiple-choice questioning (MCQ) the mainstay of their testing procedures. In Natural Language Processing (NLP), the task of autonomously generating multiple-choice questions is both beneficial and challenging. It involves using textual information to automatically generate relevant and accurate queries. Teachers find it stressful and challenging to manually generate meaningful, significant, and relevant questions, despite its importance. In our project, we describe an NLP-based method for producing MCQs on its own. Natural language processing (NLP) is an artificial intelligence field that studies how humans and computers interact with natural language. Our approach places a strong emphasis on using natural language processing (NLP) to set up multiple choice questions (MCQs). This improves the process of creating and modifying MCQs and creates a useful question bank that academics can use later on with their students. This will ensure that the multiple-choice questions (MCQ) contain options and questions relevant to the learning objectives.},
keywords = {Multiple Choice Questions, Natural Language Processing, Distractor Generation, Summary Generation, Automated Question Generation},
month = {March},
}