Event Extraction Based on the Fusion of Dynamic Prompt Information and Multi-Dimensional Features.

Event Extraction (EE) is an important part of Information Extraction (IE), whose primary mission is to automatically extract specific events and event-related arguments from the original text. This is helpful to classify, extract and reconstruct massive content. At present, most EE methods aim at single event extraction based on neural networks. However, some sentences contain multiple events, and a single argument may play different roles in different events, which is easy to cause the problem of argument role overlap. Furthermore, the latest proposed prompt learning requires too much template annotation cost. Therefore, this paper proposes a new EE method based on the self-attention mechanism, which obtains global sentence semantics by capturing the Dynamic Prompt Information (DPI) without additional manual annotation. In addition, we integrate the local sentence semantics of Multi-dimensional Event Feature (MEF) information with DPI to learn the internal correlation information between different events and different entities, so as to realize the extraction of argument multiple roles. Experiments on the widely used Automatic Content Extraction (ACE) English corpora show that our method achieves a substantial improvement over baselines. Additionally, further analysis of the extraction procedure is presented to illustrate the effectiveness of the proposed DPI and MEF.