Research on the Application of an OPT Model Integrating Meta-Learning and Prompt Learning for Few-Shot Event Extraction

Event extraction plays a pivotal role in natural language processing (NLP), especially in few-shot learning environments where research is increasingly growing. This paper proposes an OPT model that integrates Model-Agnostic Meta-Learning (MAML) and prompt learning to enhance the performance of few-shot event extraction. Our method was tested on the ACE2005 dataset and compared with existing models. The results demonstrate the effectiveness of our approach in improving few-shot event extraction.