MedICaT: A Dataset of Medical Images, Captions, and Textual References
EMNLP, pp. 2112-2120, 2020.
Understanding the relationship between figures and text is key to scientific document understanding. Medical figures in particular are quite complex, often consisting of several subfigures (75% of figures in our dataset), with detailed text describing their content. Previous work studying figures in scientific papers focused on classify...More
PPT (Upload PPT)