CUP: Curriculum Learning based Prompt Tuning for Implicit Event Argument Extraction

TL;DR

This paper introduces CUP, a curriculum learning and prompt tuning approach for implicit event argument extraction that effectively captures long-range dependencies and reduces reliance on labeled data, outperforming existing models.

Contribution

The paper proposes a novel curriculum learning framework combined with prompt tuning to improve implicit event argument extraction, especially in low-data scenarios.

Findings

Outperforms state-of-the-art models on benchmark datasets.

Effective in both fully-supervised and low-data settings.

Captures long-range dependencies via semantic graph-based curriculum stages.

Abstract

Implicit event argument extraction (EAE) aims to identify arguments that could scatter over the document. Most previous work focuses on learning the direct relations between arguments and the given trigger, while the implicit relations with long-range dependency are not well studied. Moreover, recent neural network based approaches rely on a large amount of labeled data for training, which is unavailable due to the high labelling cost. In this paper, we propose a Curriculum learning based Prompt tuning (CUP) approach, which resolves implicit EAE by four learning stages. The stages are defined according to the relations with the trigger node in a semantic graph, which well captures the long-range dependency between arguments and the trigger. In addition, we integrate a prompt-based encoder-decoder model to elicit related knowledge from pre-trained language models (PLMs) in each stage, where the prompt templates are adapted with the learning progress to enhance the reasoning for arguments. Experimental results on two well-known benchmark datasets show the great advantages of our proposed approach. In particular, we outperform the state-of-the-art models in both fully-supervised and low-data scenarios.