Enhancing Textbooks with Visuals from the Web for Improved Learning
This addresses the need for better educational materials by enhancing textbooks with visuals, but it is incremental as it applies existing methods to a new dataset.
The paper tackles the problem of textbooks lacking visuals by using vision-language models to automatically retrieve and assign web images to e-textbooks, finding through crowd-sourced evaluation that automatically assigned images are close in quality to original ones, though slightly lower.
Textbooks are one of the main mediums for delivering high-quality education to students. In particular, explanatory and illustrative visuals play a key role in retention, comprehension and general transfer of knowledge. However, many textbooks lack these interesting visuals to support student learning. In this paper, we investigate the effectiveness of vision-language models to automatically enhance textbooks with images from the web. We collect a dataset of e-textbooks in the math, science, social science and business domains. We then set up a text-image matching task that involves retrieving and appropriately assigning web images to textbooks, which we frame as a matching optimization problem. Through a crowd-sourced evaluation, we verify that (1) while the original textbook images are rated higher, automatically assigned ones are not far behind, and (2) the precise formulation of the optimization problem matters. We release the dataset of textbooks with an associated image bank to inspire further research in this intersectional area of computer vision and NLP for education.