Automated Question Generation for Science Tests in Arabic Language Using NLP Techniques

TL;DR

This paper introduces an Arabic question-generation system for educational assessments that leverages NLP techniques, achieving high precision and recall, and validated by human evaluation, to improve automatic question creation in Arabic educational technology.

Contribution

The paper presents a novel three-stage Arabic question-generation framework addressing parsing and recognition challenges, with demonstrated high accuracy and human-validated effectiveness.

Findings

Precision of 83.50% achieved

Recall of 78.68% achieved

Human evaluation rating of 84%

Abstract

Question generation for education assessments is a growing field within artificial intelligence applied to education. These question-generation tools have significant importance in the educational technology domain, such as intelligent tutoring systems and dialogue-based platforms. The automatic generation of assessment questions, which entail clear-cut answers, usually relies on syntactical and semantic indications within declarative sentences, which are then transformed into questions. Recent research has explored the generation of assessment educational questions in Arabic. The reported performance has been adversely affected by inherent errors, including sentence parsing inaccuracies, name entity recognition issues, and errors stemming from rule-based question transformation. Furthermore, the complexity of lengthy Arabic sentences has contributed to these challenges. This research presents an innovative Arabic question-generation system built upon a three-stage process: keywords and key phrases extraction, question generation, and subsequent ranking. The aim is to tackle the difficulties associated with automatically generating assessment questions in the Arabic language. The proposed approach and results show a precision of 83.50%, a recall of 78.68%, and an Fl score of 80.95%, indicating the framework high efficiency. Human evaluation further confirmed the model efficiency, receiving an average rating of 84%.