AUTOMATIC QUESTION GENERATION MODEL BASED ON DEEP LEARNING APPROACH | ||
| International Journal of Intelligent Computing and Information Sciences | ||
| Article 8, Volume 21, Issue 2, July 2021, Pages 110-123 PDF (957.67 K) | ||
| Document Type: Original Article | ||
| DOI: 10.21608/ijicis.2021.80280.1102 | ||
| Authors | ||
| Mai Mokhtar* ; Salma Doma; Hala Abdel-Galil | ||
| Computer Science Department, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, Egypt | ||
| Abstract | ||
| Nowadays, students face many difficulties to practice for exams. Professors and teachers spend a lot of time and effort to make exams. Automatic Question Generation Model proposes a solution to save time, effort, and student’s learning process which helps in educational purposes. AQGM is user-friendly which is implemented as a GUI-based system that generates Wh- questions which mean” WH” (” What”,” Who”, and” Where”) and formatted into two types of templates, Question Bank template, and Exam template. Exams have different difficulty levels (Easy, Medium, and Hard). Therefore, students can measure their level and teachers will know to what extent the students understand the course. Researches have shown that this method is helpful and successful for educational purposes. AQGM generates questions automatically by using its model that generated by using sequence-to-sequence approach specially encoder-decoder technique with copy mechanism and attention decoder. AQGM model uses SQuAD as a training dataset which helps to get more accurate results. | ||
| Keywords | ||
| Automatic Question Generation; SQuAD Dataset; Seq2seq; Feature-Rich Encoder; Attention-Based Decoder | ||
|
Statistics Article View: 610 PDF Download: 1,085 |
||
