KeyEE:Enhancing Low-Resource Generative Event Extraction with Auxiliary Keyword Sub-Prompt  

作　　者：Junwen Duan Xincheng Liao Ying An Jianxin Wang 

机构地区：[1]Hunan Key Laboratory of Bioinformatics,School of Computer Science and Engineering,Central South University,Changsha 410083,China [2]Big Data Institute,Central South University,Changsha 410083,China

出　　处：《Big Data Mining and Analytics》2024年第2期547-560,共14页大数据挖掘与分析（英文）

基　　金：supported by the National Key Research and Development Program of China(No.2021YFF1201200);the Science and Technology Major Project of Changsha(No.kh2202004);the Natural Science Foundation of China(No.62006251)。

摘　　要：Event Extraction(EE)is a key task in information extraction,which requires high-quality annotated data that are often costly to obtain.Traditional classification-based methods suffer from low-resource scenarios due to the lack of label semantics and fine-grained annotations.While recent approaches have endeavored to address EE through a more data-efficient generative process,they often overlook event keywords,which are vital for EE.To tackle these challenges,we introduce KeyEE,a multi-prompt learning strategy that improves low-resource event extraction by Event Keywords Extraction(EKE).We suggest employing an auxiliary EKE sub-prompt and concurrently training both EE and EKE with a shared pre-trained language model.With the auxiliary sub-prompt,KeyEE learns event keywords knowledge implicitly,thereby reducing the dependence on annotated data.Furthermore,we investigate and analyze various EKE sub-prompt strategies to encourage further research in this area.Our experiments on benchmark datasets ACE2005 and ERE show that KeyEE achieves significant improvement in low-resource settings and sets new state-of-the-art results.

关 键 词：natural language processing Event Extraction(EE) Multi-Prompt Learning(MPL) low-resource 

分 类 号：TP391.44[自动化与计算机技术—计算机应用技术] TN915.08[自动化与计算机技术—计算机科学与技术]