DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extraction
This addresses the problem of event extraction in low-resource domains for NLP researchers, offering a novel approach but with incremental improvements over existing paradigms.
The paper tackles low-resource event extraction by proposing DemoSG, a model that uses demonstration-based learning and schema-guided generation, and it significantly outperforms current methods in experiments on three datasets under low-resource settings.
Most current Event Extraction (EE) methods focus on the high-resource scenario, which requires a large amount of annotated data and can hardly be applied to low-resource domains. To address EE more effectively with limited resources, we propose the Demonstration-enhanced Schema-guided Generation (DemoSG) model, which benefits low-resource EE from two aspects: Firstly, we propose the demonstration-based learning paradigm for EE to fully use the annotated data, which transforms them into demonstrations to illustrate the extraction process and help the model learn effectively. Secondly, we formulate EE as a natural language generation task guided by schema-based prompts, thereby leveraging label semantics and promoting knowledge transfer in low-resource scenarios. We conduct extensive experiments under in-domain and domain adaptation low-resource settings on three datasets, and study the robustness of DemoSG. The results show that DemoSG significantly outperforms current methods in low-resource scenarios.