摘要
实体关系抽取是信息抽取领域的重要任务之一,也是知识图谱构建的一个关键环节.现有的关系抽取方法大多都是围绕实体对从句子中抽取上下文语义特征,然后进行关系分类,这忽略了实体在整个语料集中的全局上下文特征.本文提出了一种新颖的结合实体共现信息与句子语义信息的神经网络(CNSSNN)模型,用于实体关系抽取.该模型首先构造整个语料集蕴含的实体共现关系网络,并通过引入注意力机制有侧重地提取实体的网络环境信息,从而为各个实体生成语料级全局上下文特征,同时利用双向门控循环单元网络(bi-GRU)为实体对提取句子级上下文语义特征,最后将语料级特征和句子级特征结合起来,进行实体关系抽取.在公开数据集和人工标注的数据集上的实验结果表明,本文提出的方法其准确率和召回率要明显优于其他现有方法.
Relation extraction is one of the most important tasks in information extraction and a key step in knowledge graph construction. The existing relation extraction approaches mostly try to capture semantic features for entity pairs at the sentence level, which might ignore the global context information of the entities in the entire corpus. In this paper, we propose a novel neural network model for relation extraction, named CNSSNN,which combines the information of entity co-occurrences with sentences＇ semantic features. In this model, we first build an entity co-occurrence network from the corpus. Then, we introduce a network-level attention mechanism to capture network environmental information selectively and generate the corpus-level global context features for the entities. At the same time, we employ a bi-directional gated recurrent unit（bi-GRU） network to extract sentence-level semantic features for entity pairs. Finally, we combine the corpus-level features and the sentencelevel features to classify relations. The experimental results, over a manually labeled dataset, show that our approach consistently outperforms other existing approaches in terms of both precision and recall.
作者
马语丹
赵义
金婧
万怀宇
Yudan MA;Yi ZHAO;Jing JIN;Huaiyu WAN(Beijing Key Laboratory of Traffic Data Analysis and Mining,School of Computer and Information Technology Beijing Jiaotong University,Beijing 100044,China)
出处
《中国科学：信息科学》
CSCD
北大核心
2018年第11期1533-1545,共13页
Scientia Sinica(Informationis)
基金
国家重点研发计划(批准号:2018YFC0830200)资助项目
关键词
信息抽取
实体关系抽取
实体共现网络
注意力机制
门控循环单元
information extraction
entity relation extraction
entity co-occurrence network
attention mecha-nism
gated recurrent unit
