Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker

TL;DR

This paper introduces GIT, a novel heterogeneous graph-based model with a tracker for document-level event extraction, effectively capturing global interactions and event interdependencies to improve extraction accuracy.

Contribution

The paper proposes a new GIT model that addresses key challenges in document-level event extraction by modeling global interactions and event dependencies with a heterogeneous graph and tracker.

Findings

GIT outperforms previous methods by 2.8 F1 on a large-scale dataset.

GIT effectively extracts multiple correlated events and scattered arguments.

The approach demonstrates strong capability in modeling complex event interdependencies.

Abstract

Document-level event extraction aims to recognize event information from a whole piece of article. Existing methods are not effective due to two challenges of this task: a) the target event arguments are scattered across sentences; b) the correlation among events in a document is non-trivial to model. In this paper, we propose Heterogeneous Graph-based Interaction Model with a Tracker (GIT) to solve the aforementioned two challenges. For the first challenge, GIT constructs a heterogeneous graph interaction network to capture global interactions among different sentences and entity mentions. For the second, GIT introduces a Tracker module to track the extracted events and hence capture the interdependency among the events. Experiments on a large-scale dataset (Zheng et al., 2019) show GIT outperforms the previous methods by 2.8 F1. Further analysis reveals GIT is effective in extracting multiple correlated events and event arguments that scatter across the document. Our code is available at https://github.com/RunxinXu/GIT.