摘要
从非结构化文本中联合提取实体和关系是信息抽取中的一项重要任务。现有方法取得了可观的性能,但仍受到一些固有的限制,如错误传播、预测存在冗余性、无法解决关系重叠问题等。为此,提出一种基于图神经网络的联合实体关系抽取模型BSGB(BiLSTM+SDA-GAT+BiGCN)。BSGB分为两个阶段:第一阶段将语义依存分析扩展到语义依存图,提出融合语义依存图的图注意力网络(SDA-GAT),通过堆叠BiLSTM和SDA-GAT提取句子序列和局部依赖特征,并进行实体跨度检测和初步的关系预测;第二阶段构建关系加权GCN,进一步建模实体和关系的交互,完成最终的实体关系三元组抽取。在NYT数据集上的实验结果表明,该模型F_(1)值达到了67.1%,对比在该数据集的基线模型提高了5.2%,对重叠关系的预测也有大幅改善。
Joint extraction of entities and relations from unstructured text is an important task in information extraction.The existing methods have achieved considerable performance,but are still subject to some inherent limitations,such as error propagation,redundancy of relation prediction,inability to solve the problem of relations overlap,etc.For this reason,this paper proposed a joint entity relationship extraction model BSGB(BiLSTM+SDA-GAT+BiGCN)based on graph neural network.BSGB was a two-stage predicting process.The first stage of this model extended the semantic dependency analysis to the semantic dependency graph,and proposed a graph attention network to integrate the semantic dependency graph(SDA-GAT).By stacking BiLSTM and SDA-GAT,it extracted sentence sequence and local dependent features,and performed entity span detection and preliminary relationship prediction.In the second stage,it constructed the relation-weighted GCN,which further modeled the interaction between entities and relations,and completed the final extraction of entity-relationship triples.The experimental results on the NYT dataset show that the F_(1) value of this model reaches 67.1%,which is 5.2%higher than the baseline model in this dataset,and the prediction of the overlap relation is also significantly improved.
作者
苗琳
张英俊
谢斌红
李玉
Miao Lin;Zhang Yingjun;Xie Binhong;Li Yu(College of Computer Science&Technology,Taiyuan University of Science&Technology,Taiyuan 030024,China)
出处
《计算机应用研究》
CSCD
北大核心
2022年第2期424-431,共8页
Application Research of Computers
基金
山西省重点研发计划资助项目(201703D111027,201803D121048,201803D121055)。
关键词
联合实体关系抽取
图注意力网络
语义依存图
joint entity relation extraction
graph attention network(GAT)
semantic dependency graph
