DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Based Event Argument Extraction with Slot Querying

TL;DR

DEGAP introduces dual learnable prefixes and an adaptive gating mechanism to improve event argument extraction, achieving state-of-the-art results without relying on retrieval of irrelevant information.

Contribution

The paper proposes a novel dual prefix and event-guided gating approach that enhances event argument extraction by capturing event relationships without retrieval.

Findings

Achieves new state-of-the-art performance on four datasets.

Effective in leveraging event relationships without retrieval.

Components significantly impact model performance.

Abstract

Recent advancements in event argument extraction (EAE) involve incorporating useful auxiliary information into models during training and inference, such as retrieved instances and event templates. These methods face two challenges: (1) the retrieval results may be irrelevant and (2) templates are developed independently for each event without considering their possible relationship. In this work, we propose DEGAP to address these challenges through a simple yet effective components: dual prefixes, i.e. learnable prompt vectors, where the instance-oriented prefix and template-oriented prefix are trained to learn information from different event instances and templates. Additionally, we propose an event-guided adaptive gating mechanism, which can adaptively leverage possible connections between different events and thus capture relevant information from the prefix. Finally, these event-guided prefixes provide relevant information as cues to EAE model without retrieval. Extensive experiments demonstrate that our method achieves new state-of-the-art performance on four datasets (ACE05, RAMS, WIKIEVENTS, and MLEE). Further analysis shows the impact of different components.