Few-Shot Document-Level Event Argument Extraction

TL;DR

This paper introduces FewDocAE, a new benchmark for document-level event argument extraction in few-shot settings, highlighting the challenges and encouraging further research in low-resource, cross-sentence argument extraction.

Contribution

It defines a new few-shot document-level event argument extraction task and provides baseline models and a reconstructed dataset for future research.

Findings

The task is highly challenging with low baseline performance.

The benchmark emphasizes the difficulty of cross-sentence argument extraction.

Few-shot models need significant improvement for practical use.

Abstract

Event argument extraction (EAE) has been well studied at the sentence level but under-explored at the document level. In this paper, we study to capture event arguments that actually spread across sentences in documents. Prior works usually assume full access to rich document supervision, ignoring the fact that the available argument annotation is usually limited. To fill this gap, we present FewDocAE, a Few-Shot Document-Level Event Argument Extraction benchmark, based on the existing document-level event extraction dataset. We first define the new problem and reconstruct the corpus by a novel N -Way-D-Doc sampling instead of the traditional N -Way-K-Shot strategy. Then we adjust the current document-level neural models into the few-shot setting to provide baseline results under in- and cross-domain settings. Since the argument extraction depends on the context from multiple sentences and the learning process is limited to very few examples, we find this novel task to be very challenging with substantively low performance. Considering FewDocAE is closely related to practical use under low-resource regimes, we hope this benchmark encourages more research in this direction. Our data and codes will be available online.