Yuki Chida


2023

pdf bib
Medical Visual Textual Entailment for Numerical Understanding of Vision-and-Language Models
Hitomi Yanaka | Yuta Nakamura | Yuki Chida | Tomoya Kurosawa
Proceedings of the 5th Clinical Natural Language Processing Workshop

Assessing the capacity of numerical understanding of vision-and-language models over images and texts is crucial for real vision-and-language applications, such as systems for automated medical image analysis. We provide a visual reasoning dataset focusing on numerical understanding in the medical domain. The experiments using our dataset show that current vision-and-language models fail to perform numerical inference in the medical domain. However, the data augmentation with only a small amount of our dataset improves the model performance, while maintaining the performance in the general domain.