Improving Event Extraction via Multimodal Integration
MM '17: ACM Multimedia Conference Mountain View California USA October, 2017, pp. 270-278, 2017.
In this paper, we focus on improving Event Extraction (EE) by incorporating visual knowledge with words and phrases from text documents. We first discover visual patterns from large-scale text-image pairs in a weakly-supervised manner and then propose a multimodal event extraction algorithm where the event extractor is jointly trained wit...More