Automated Multiple Choice Question Generation
Author(s):
G. Naveen
Keywords:
Data Mining, Ontology, Semantic Web, Multiple Choice Question (MCQ) Generation, Deep Learning, Natural Language Processing (NLP), Google BERT, Long Short-Term Memory, Vanishing Gradient Problem, Stanford Question Answering Dataset, Automated Question Generation, Text Summarization, Machine Learning Models.
Abstract
Data mining involves extracting valuable insights from raw data, which is then organized into a useful format. Techniques such as prediction, classification, clustering, and rule mining enable businesses to make proactive decisions based on data that would be cumbersome to process manually. Ontology, the process of extracting useful information from extensive data sources, has become a key area of research, particularly in the context of the semantic web. One emerging challenge is Multiple Choice Question (MCQ) generation, which requires creating questions from given phrases or text. Traditional models using Long Short-Term Memory (LSTM) networks faced limitations, including issues like the vanishing gradient problem and suboptimal accuracy with large datasets. To address these issues, the proposed On toque system employs the Google BERT model, a Deep Learning NLP tool capable of handling extensive text and generating MCQs dynamically. Evaluated using the Stanford Question Answering Dataset, which includes over 100,000 questions from SQuAD1.1 and 50,000 adversarial written unanswerable questions, OntoQue demonstrated the ability to accurately generate MCQs from various text summaries, surpassing previous models in performance.
Article Details
Unique Paper ID: 167199

Publication Volume & Issue: Volume 11, Issue 3

Page(s): 512 - 518
Article Preview & Download


Share This Article

Join our RMS



Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Latest Publication

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on [email protected]

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: [email protected]
Website: ijirt.org

Policies

Important Links

Browse Rsearch papers