基于多任务深度学习的实体和事件联合抽取模型  

Joint Extraction Model for Entities and Events with Multi-task Deep Learning

作　　者：余传明[1] 林虹君 张贞港 Yu Chuanming;Lin Hongjun;Zhang Zhengang(School of Information and Safety Engineering,Zhongnan University of Economics and Law,Wuhan 430073,China)

机构地区：[1]中南财经政法大学信息与安全工程学院,武汉430073

出　　处：《数据分析与知识发现》2022年第2期117-128,共12页Data Analysis and Knowledge Discovery

基　　金：国家自然科学基金面上项目(项目编号:71974202);国家自然科学基金重大课题(项目编号:71790612)的研究成果之一。

摘　　要：【目的】利用命名实体识别与事件检测任务之间的相关性,同时提升命名实体识别和事件检测模型的性能。【方法】提出基于多任务学习的实体和事件联合抽取模型MDL-J3E,该模型分为共享层、私有层和解码层。其中,共享层生成通用特征;私有层由命名实体识别部分和事件检测部分组成,在通用特征的基础上分别提取两个子任务的私有特征;解码层将子任务的特征解码输出为符合约束规则的标签序列。【结果】在ACE2005数据集上开展实证研究,所提模型在命名实体识别任务上的F1值为84.15%,在事件检测任务上的F1值为70.96%。【局限】未将多任务模型应用到更多的信息抽取场景中。【结论】与单任务模型相比,多任务模型在命名实体识别任务和事件检测任务中具有更好的效果。[Objective]The study tries to improve the performance of entity and event extraction with the help of their correlation.[Methods]Based on the multi-task deep learning,we proposed a joint entity and event extraction model(MDL-J3E),which had the shared layer,the private layer,and the decoding layer.The shared layer generated common features.The private layer had the named entity recognition and event detection modules,which extracted features of the two subtasks based on their general features.The decoding layer analyzed features of each task and generated tag sequence following the constraint rules.[Results]We examined our model with the ACE2005 dataset.The F1 values were 84.15%in the named entity recognition task and 70.96%in the event detection task.[Limitations]We did not evaluate the proposed model with other information extraction scenarios.[Conclusions]Compared with the single task model,our multi-task model has better performance in both named entity recognition and event detection tasks.

关 键 词：命名实体识别 事件检测 多任务学习 深度学习 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]