This paper addresses the extraction of event records from documents that describe multiple events. Specifically, we aim to identify the fields of information contained in a document and aggregate together those fields that describe the same event. To exploit the inherent connections between field extraction and event identification, we propose to model them jointly. Our model is novel in that it
integrates information from separate sequential models, using global potentials that encourage the extracted event records to have desired properties. While the model contains high-order potentials, efficient approximate inference can be performed with dual-decomposition. We experiment with two data sets that consist of newspaper articles describing multiple terrorism events, and show that our model substantially outperforms traditional pipeline models.