Automatic grading for Arabic short answer questions using optimized deep learning model

• Published in: PloS one Vol. 17; no. 8; p. e0272269
• Main Authors: Abdul Salam, Mustafa, El-Fatah, Mohamed Abd, Hassan, Naglaa Fathy
• Format: Journal Article
• Language: English
• Published: San Francisco Public Library of Science 02.08.2022; Public Library of Science (PLoS)
• Subjects: Algorithms; Analysis; Arabic language; Biology and Life Sciences; Computational linguistics; Computer and Information Sciences; Correlation; Correlation coefficient; Correlation coefficients; Datasets; Deep learning; Engineering and Technology; Evaluation; Hybrid systems; Language processing; Long short-term memory; Machine learning; Modelling; Natural language interfaces; Natural language processing; Optimization; Optimization techniques; Physical Sciences; Questions; Research and Analysis Methods; Root-mean-square errors; Semantics; Social Sciences; Students; Egypt

Auto-grading of short answer questions is considered a challenging problem in the processing of natural language. It requires a system to comprehend the free text answers to automatically assign a grade for a student answer compared to one or more model answers. This paper suggests an optimized deep...