We study the new problem of automatic question generation (QG) from multi-modal sources containing images and texts, significantly expanding the scope of most of the existing work that focuses exclusively on QG from only textual sources. We propose a simple solution for our new problem, called MultiQG-TI, which enables a text-only question generator to process visual input in addition to textual input. Specifically, we leverage an image-to-text model and an optical character recognition model to obtain the textual description of the image and extract any texts in the image, respectively, and then feed them together with the input texts to the question generator. We only fine-tune the question generator while keeping the other components fixed. On the challenging ScienceQA dataset, we demonstrate that MultiQG-TI significantly outperforms ChatGPT with few-shot prompting, despite having hundred-times less trainable parameters. Additional analyses empirically confirm the necessity of both visual and textual signals for QG and show the impact of various modeling choices.

翻译：我们研究了从包含图像和文本的多模态资源中自动生成问题（QG）这一新问题，显著扩展了大多数现有工作仅聚焦于文本资源问题生成的研究范畴。针对这一新问题，我们提出了一种名为MultiQG-TI的简洁解决方案，使纯文本问题生成器能够同时处理视觉输入与文本输入。具体而言，我们利用图像到文本模型和光学字符识别模型分别获取图像的文本描述并提取图像中的文字信息，随后将这些信息与输入文本一同馈入问题生成器。我们仅对问题生成器进行微调，而保持其他组件固定不变。在具有挑战性的ScienceQA数据集上，我们证明了MultiQG-TI在可训练参数量少百倍的情况下，其性能显著优于采用少样本提示的ChatGPT。进一步分析通过实验证实了视觉信号和文本信号对问题生成的必要性，并展示了不同建模选择的影响。