What Did This Castle Look Like Before? Exploring Referential Relations in Naturally Occurring Multimodal Texts

摘要

Multi-modal texts are abundant and diverse in structure, yet Vision & Language research of these naturally occurring texts has mostly focused on genres that are comparatively light on text, like tweets. In this paper, we discuss the challenges and potential benefits of a V&L framework that explicitly models referential relations, taking Wikipedia articles about buildings as an example. We briefly survey existing related tasks in V&L and propose multi-modal information extraction as a general direction for future research.