arXiv:2501.06825cs.CL2025-01被引 1

通过增强提示信息提升事件论元抽取效果

Event Argument Extraction with Enriched Prompts

  • 在提示中加入触发词、同事件及跨事件论元信息
  • 在RAMS数据集上实现当前提示模型最佳性能
  • 适用于需要高精度事件分析的自然语言处理任务

本研究深入探索基于提示的事件论元抽取(EAE)模型。我们考察了将不同类型的上下文信息融入提示对模型性能的影响,包括同一事件中的触发词、其他角色论元,以及同一文档中跨事件的角色论元。此外,我们评估了提示式EAE模型所能达到的最佳表现,并从训练目标角度证明其可进一步优化。实验在三个小型语言模型和两个大型语言模型上于RAMS数据集上进行。

原文摘要 · Abstract (English)

This work aims to delve deeper into prompt-based event argument extraction (EAE) models. We explore the impact of incorporating various types of information into the prompt on model performance, including trigger, other role arguments for the same event, and role arguments across multiple events within the same document. Further, we provide the best possible performance that the prompt-based EAE model can attain and demonstrate such models can be further optimized from the perspective of the training objective. Experiments are carried out on three small language models and two large language models in RAMS.

事件抽取提示学习自然语言处理

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。