融合多特征BERT模型的中文实体关系抽取  

Chinese Entity Relation Extraction Based on Multi-Feature BERT Model

作　　者：谢腾 杨俊安 刘辉[1] XIE Teng;YANG Jun-An;LIU Hui(College of Electronic Engineering,National University of Defense Technology,Hefei 230031,China)

机构地区：[1]国防科技大学电子对抗学院,合肥230031

出　　处：《计算机系统应用》2021年第5期253-261,共9页Computer Systems & Applications

基　　金：安徽省自然科学基金(1908085MF202)。

摘　　要：关系抽取是构建知识图谱的一项核心技术.由于中文具有复杂的语法和句式,同时现有的神经网络模型提取特征有限以及语义表征能力较差,从而影响中文实体关系抽取的性能.文章提出了一种融合多特征的BERT预训练模型的实体关系抽取算法.首先对语料进行预处理,提取关键词、实体对信息和实体类型特征并进行融合,以此来强化BERT模型的语义学习能力,极大限度地减少了语义信息特征的丢失,最后通过Softmax分类器进行关系分类.实验结果表明,文章模型优于现有的神经网络模型.在人工标注的中文数据集上本文模型取得了97.50%的F1值.Relation extraction is a core technology to construct a knowledge graph.The complexity of Chinese grammar and sentence structure as well as the limited feature extraction and poor semantic representation of the existing neural network model restrict the relation extraction of Chinese entities.A relation extraction algorithm based on a BERT pretraining model is proposed in this study.It preprocesses the corpus by extracting keywords,entity pairs and entity type and integrating them to strengthen the semantic learning ability of the BERT model,greatly reducing the loss of semantic features.Results are obtained by a Softmax classifier,which show that this model is better than the existing neural network model.In particular,the model reaches a F1-score of 97.50%on the Chinese data set.

关 键 词：实体关系抽取 双向编码表征模型 词向量 外部特征 特征融合 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]