Global Constraints with Prompting for Zero-Shot Event Argument Classification

TL;DR

This paper introduces a zero-shot event argument classification method using global constraints and prompting, eliminating the need for annotated training data and achieving significant performance improvements.

Contribution

It presents a novel prompting-based approach with global constraints for zero-shot event argument classification, adaptable to all event types without manual effort.

Findings

Outperforms zero-shot baselines by 12.5% and 10.9% F1 on ACE and ERE datasets.

Achieves 4.3% and 3.3% F1 improvements without argument span annotations.

Effective in open-domain event argument classification without task-specific training.

Abstract

Determining the role of event arguments is a crucial subtask of event extraction. Most previous supervised models leverage costly annotations, which is not practical for open-domain applications. In this work, we propose to use global constraints with prompting to effectively tackles event argument classification without any annotation and task-specific training. Specifically, given an event and its associated passage, the model first creates several new passages by prefix prompts and cloze prompts, where prefix prompts indicate event type and trigger span, and cloze prompts connect each candidate role with the target argument span. Then, a pre-trained language model scores the new passages, making the initial prediction. Our novel prompt templates can easily adapt to all events and argument types without manual effort. Next, the model regularizes the prediction by global constraints exploiting cross-task, cross-argument, and cross-event relations. Extensive experiments demonstrate our model's effectiveness: it outperforms the best zero-shot baselines by 12.5% and 10.9% F1 on ACE and ERE with given argument spans and by 4.3% and 3.3% F1, respectively, without given argument spans. We have made our code publicly available.