EventGraph: Event Extraction as Semantic Graph Parsing

TL;DR

EventGraph introduces a novel joint graph-based framework for event extraction that simultaneously detects events and their arguments, capturing complex interactions and improving argument extraction performance.

Contribution

The paper presents a unified graph parsing approach for event extraction, enabling joint detection and argument extraction, and introduces new datasets with full argument spans.

Findings

Competitive performance on ACE2005

Significant improvement in argument extraction accuracy

Effective modeling of event argument interactions

Abstract

Event extraction involves the detection and extraction of both the event triggers and corresponding event arguments. Existing systems often decompose event extraction into multiple subtasks, without considering their possible interactions. In this paper, we propose EventGraph, a joint framework for event extraction, which encodes events as graphs. We represent event triggers and arguments as nodes in a semantic graph. Event extraction therefore becomes a graph parsing problem, which provides the following advantages: 1) performing event detection and argument extraction jointly; 2) detecting and extracting multiple events from a piece of text; and 3) capturing the complicated interaction between event arguments and triggers. Experimental results on ACE2005 show that our model is competitive to state-of-the-art systems and has substantially improved the results on argument extraction. Additionally, we create two new datasets from ACE2005 where we keep the entire text spans for event arguments, instead of just the head word(s). Our code and models are released as open-source.