Event Extraction by Answering (Almost) Natural Questions

TL;DR

This paper introduces a novel event extraction approach that formulates the task as a question answering problem, enabling end-to-end extraction and zero-shot learning, outperforming previous methods.

Contribution

The paper proposes a new paradigm for event extraction using QA formulation, reducing error propagation and enabling zero-shot argument extraction.

Findings

Outperforms prior event extraction methods significantly

Capable of zero-shot event argument extraction

Effective end-to-end event extraction framework

Abstract

The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments. Existing work in event argument extraction typically relies heavily on entity recognition as a preprocessing/concurrent step, causing the well-known problem of error propagation. To avoid this issue, we introduce a new paradigm for event extraction by formulating it as a question answering (QA) task that extracts the event arguments in an end-to-end manner. Empirical results demonstrate that our framework outperforms prior methods substantially; in addition, it is capable of extracting event arguments for roles not seen at training time (zero-shot learning setting).