Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction

TL;DR

This paper introduces a bi-directional iterative prompt-tuning approach for event argument extraction that leverages entity information and argument interactions, significantly improving performance over existing methods.

Contribution

It proposes a novel prompt-tuning framework that incorporates entity roles and semantic verbalizers for enhanced event argument extraction.

Findings

Outperforms state-of-the-art methods on ACE 2005 dataset.

Effective in both standard and low-resource settings.

Utilizes semantic role knowledge for prompt construction.

Abstract

Recently, prompt-tuning has attracted growing interests in event argument extraction (EAE). However, the existing prompt-tuning methods have not achieved satisfactory performance due to the lack of consideration of entity information. In this paper, we propose a bi-directional iterative prompt-tuning method for EAE, where the EAE task is treated as a cloze-style task to take full advantage of entity information and pre-trained language models (PLMs). Furthermore, our method explores event argument interactions by introducing the argument roles of contextual entities into prompt construction. Since template and verbalizer are two crucial components in a cloze-style prompt, we propose to utilize the role label semantic knowledge to construct a semantic verbalizer and design three kinds of templates for the EAE task. Experiments on the ACE 2005 English dataset with standard and low-resource settings show that the proposed method significantly outperforms the peer state-of-the-art methods. Our code is available at https://github.com/HustMinsLab/BIP.