Improving Event Extraction via Multimodal Integration

  • Tongtao Zhang ,
  • Spencer Whitehead ,
  • Hanwang Zhang ,
  • Hongzhi Li ,
  • Joseph Ellis ,
  • Lifu Huang ,
  • Wei Liu ,
  • Heng Ji ,
  • Shih-Fu Chang

Proceedings of the 25th ACM international conference on Multimedia |

Published by ACM

Download BibTex

In this paper, we focus on improving Event Extraction (EE) by incorporating visual knowledge with words and phrases from text documents. We €rst discover visual paŠerns from large-scale textimage pairs in a weakly-supervised manner and then propose a multimodal event extraction algorithm where the event extractor is jointly trained with textual features and visual paŠerns. Extensive experimental results on benchmark data sets demonstrate that the proposed multimodal EE method can achieve signi€cantly beŠer performance on event extraction: absolute 7.1% F-score gain on event trigger labeling and 8.5% F-score gain on event argument labeling.