Explicit, Implicit, and Scattered: Revisiting Event Extraction to Capture Complex Arguments

TL;DR

This paper introduces a new approach to event extraction that captures explicit, implicit, and scattered arguments, supported by a novel dataset and a text generation formulation, advancing the understanding of complex event modeling.

Contribution

The paper presents DiscourseEE, a dataset with diverse argument types, and formulates event argument extraction as a text generation task to handle complex arguments.

Findings

51.2% of arguments are implicit

17.4% of arguments are scattered

Generative models face open challenges in complex event extraction

Abstract

Prior works formulate the extraction of event-specific arguments as a span extraction problem, where event arguments are explicit -- i.e. assumed to be contiguous spans of text in a document. In this study, we revisit this definition of Event Extraction (EE) by introducing two key argument types that cannot be modeled by existing EE frameworks. First, implicit arguments are event arguments which are not explicitly mentioned in the text, but can be inferred through context. Second, scattered arguments are event arguments that are composed of information scattered throughout the text. These two argument types are crucial to elicit the full breadth of information required for proper event modeling. To support the extraction of explicit, implicit, and scattered arguments, we develop a novel dataset, DiscourseEE, which includes 7,464 argument annotations from online health discourse. Notably, 51.2% of the arguments are implicit, and 17.4% are scattered, making DiscourseEE a unique corpus for complex event extraction. Additionally, we formulate argument extraction as a text generation problem to facilitate the extraction of complex argument types. We provide a comprehensive evaluation of state-of-the-art models and highlight critical open challenges in generative event extraction. Our data and codebase are available at https://omar-sharif03.github.io/DiscourseEE.