@inproceedings{2d860429d2db4b8691b4c61b82dee95f,
title = "Improving event extraction via multimodal integration",
abstract = "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 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 patterns. Extensive experimental results on benchmark data sets demonstrate that the proposed multimodal EE method can achieve significantly better performance on event extraction: absolute 7.1% F-score gain on event trigger labeling and 8.5% F-score gain on event argument labeling.",
keywords = "Event extraction, Multimodal approach, Natural language processing, Visual pattern discovery",
author = "Tongtao Zhang and Spencer Whitehead and Hanwang Zhang and Hongzhi Li and Joseph Ellis and Lifu Huang and Wei Liu and Heng Ji and Chang, {Shih Fu}",
note = "Publisher Copyright: {\textcopyright} 2017 Association for Computing Machinery.; 25th ACM International Conference on Multimedia, MM 2017 ; Conference date: 23-10-2017 Through 27-10-2017",
year = "2017",
month = oct,
day = "23",
doi = "10.1145/3123266.3123294",
language = "English (US)",
series = "MM 2017 - Proceedings of the 2017 ACM Multimedia Conference",
publisher = "Association for Computing Machinery",
pages = "270--278",
booktitle = "MM 2017 - Proceedings of the 2017 ACM Multimedia Conference",
address = "United States",
}