基于课程图示生成精准问题，助力教育评估
Diagram-Driven Course Questions Generation
- 用课程和文本约束引导图示元素提问，确保内容相关性
- 在15,720张图、25,798个问题的DiagramQG数据集上表现领先
- 适合教育AI、智能题库研发者参考
视觉问答生成（VQG）研究多集中于自然图像，忽视了教育材料中关键的图示。为满足教学评估需求，我们提出图示驱动的课程问题生成（DDCQG）任务，并构建了包含15,720张图、25,798个问题的DiagramQG数据集，覆盖37个学科和371门课程。方法结合课程与输入文本约束，生成关于特定图示元素的课程相关问题。揭示了三大挑战：跨课程领域知识要求高、课程覆盖长尾分布、图示信息密度大。为此提出分层知识融合框架HKI-DDCQG：使用可训练CLIP识别相关图块，利用冻结的视觉-语言模型提取知识，通过可训练T5生成问题。实验表明，HKI-DDCQG在DiagramQG上优于现有模型，且在自然图像数据集上仍具强泛化能力，确立了DDCQG的坚实基线。
原文摘要 · Abstract (English)
Visual Question Generation (VQG) research focuses predominantly on natural images while neglecting the diagram, which is a critical component in educational materials. To meet the needs of pedagogical assessment, we propose the Diagram-Driven Course Questions Generation (DDCQG) task and construct DiagramQG, a comprehensive dataset with 15,720 diagrams and 25,798 questions across 37 subjects and 371 courses. Our approach employs course and input text constraints to generate course-relevant questions about specific diagram elements. We reveal three challenges of DDCQG: domain-specific knowledge requirements across courses, long-tail distribution in course coverage, and high information density in diagrams. To address these, we propose the Hierarchical Knowledge Integration framework (HKI-DDCQG), which utilizes trainable CLIP for identifying relevant diagram patches, leverages frozen vision-language models for knowledge extraction, and generates questions with trainable T5. Experiments demonstrate that HKI-DDCQG outperforms existing models on DiagramQG while maintaining strong generalizability across natural image datasets, establishing a strong baseline for DDCQG.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。