Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction
This addresses the problem of inefficient and isolated event processing in document-level information extraction for NLP applications, representing a novel method rather than an incremental improvement.
The paper tackles the inefficiency and lack of correlation handling in single-event argument extraction by proposing DEEIA, a model that extracts arguments for all events in a document simultaneously, achieving state-of-the-art performance on four datasets and significantly reducing inference time.
Recent mainstream event argument extraction methods process each event in isolation, resulting in inefficient inference and ignoring the correlations among multiple events. To address these limitations, here we propose a multiple-event argument extraction model DEEIA (Dependency-guided Encoding and Event-specific Information Aggregation), capable of extracting arguments from all events within a document simultaneouslyThe proposed DEEIA model employs a multi-event prompt mechanism, comprising DE and EIA modules. The DE module is designed to improve the correlation between prompts and their corresponding event contexts, whereas the EIA module provides event-specific information to improve contextual understanding. Extensive experiments show that our method achieves new state-of-the-art performance on four public datasets (RAMS, WikiEvents, MLEE, and ACE05), while significantly saving the inference time compared to the baselines. Further analyses demonstrate the effectiveness of the proposed modules.