• ISSN: 2349-6002
  • UGC Approved Journal No 47859

Automated Multiple Choice Question Generation

  • Unique Paper ID: 167199
  • Volume: 11
  • Issue: 3
  • PageNo: 512-518
  • 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.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 3
  • PageNo: 512-518

Automated Multiple Choice Question Generation

Related Articles