Noisy and Unbalanced Multimodal Document Classification: Textbook Exercises as a Use Case

In order to foster inclusive education, automatic systems that can adapt textbooks to make them accessible to children with Developmental Coordination Disorder (DCD) are necessary. In this context, we propose a task to classify exercises according to their DCD adaptation type. We introduce a challenging exercise dataset extracted from French textbooks, with two major difficulties: limited and unbalanced, noisy data. To set a baseline on the dataset, we use state-of-the-art models combined through early and late fusion techniques to take advantage of text and vision/layout modalities. Our approach achieves an overall accuracy of 0.802. However, the experiments show the difficulty of the task, especially for minority classes, where the accuracy drops to 0.583.