A Rule-Based Automatic Question Generation Framework for Educational Text

Abstract

Automatic Question Generation (AQG) is essential in educational technology, enabling the creation of assessments, practice exercises, and intelligent tutoring systems. Although recent neural approaches have achieved promising results, they often lack interpretability and control, thereby limiting their use in structured educational contexts. To overcome these challenges, this study introduces a structurally modular, rule-based AQG framework that generates factoid questions from educational texts through explicit linguistic rules and deterministic transformations. The proposed framework draws on classical rule-based question generation methods and employs a two-stage algorithmic design that distinctly separates linguistic analysis from question generation. The first stage involves linguistic preprocessing, clause extraction, and auxiliary-verb determination to identify syntactically valid, question-worthy clauses. In the second stage, rule-based transformations generate various factoid question types, such as who, what, where, when, how many, and how much, followed by disambiguation, template-based surface real- ization, and validation. This separation enhances interpretability, extensibility, and control over rule execution. Unlike data-driven models, the proposed framework does not require annotated training data and avoids hallucination by relying on explicit syntactic and semantic patterns. The resulting system produces grammatically correct, semantically meaningful, and reproducible questions, making it well suited for educational and academic applications. The study demonstrates that carefully designed rule-based systems remain a viable and effective alternative for automatic question generation in controlled domains.