A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education

This paper introduces a Topic-Controlled Question Generation (T-CQG) method using fine-tuned T5-small models to automatically generate topic-specific educational questions from paragraph contexts, aiming to reduce teacher workload in creating assessment content. The work evaluates generated question quality through offline metrics and human evaluation, focusing on topical alignment and semantic relevance to K-12 educational needs.

The development of Automatic Question Generation (QG) models has the potential to significantly improve educational practices by reducing the teacher workload associated with creating educational content. This paper introduces a novel approach to educational question generation that controls the topical focus of questions. The proposed Topic-Controlled Question Generation (T-CQG) method enhances the relevance and effectiveness of the generated content for educational purposes. Our approach uses

Study Type

Source

Framework Categories

Tool Types

Tags