Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,...Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,sentiment analysis and question-answering systems.However,previous studies ignored much unusedstructural information in sentences that could enhance the performance of the relation extraction task.Moreover,most existing dependency-based models utilize self-attention to distinguish the importance of context,whichhardly deals withmultiple-structure information.To efficiently leverage multiple structure information,this paperproposes a dynamic structure attention mechanism model based on textual structure information,which deeplyintegrates word embedding,named entity recognition labels,part of speech,dependency tree and dependency typeinto a graph convolutional network.Specifically,our model extracts text features of different structures from theinput sentence.Textual Structure information Graph Convolutional Networks employs the dynamic structureattention mechanism to learn multi-structure attention,effectively distinguishing important contextual features invarious structural information.In addition,multi-structure weights are carefully designed as amergingmechanismin the different structure attention to dynamically adjust the final attention.This paper combines these featuresand trains a graph convolutional network for relation extraction.We experiment on supervised relation extractiondatasets including SemEval 2010 Task 8,TACRED,TACREV,and Re-TACED,the result significantly outperformsthe previous.展开更多
In the link prediction task of knowledge graph completion,Graph Neural Network(GNN)-based knowledge graph completion models have been shown by previous studies to produce large improvements in prediction results.Howev...In the link prediction task of knowledge graph completion,Graph Neural Network(GNN)-based knowledge graph completion models have been shown by previous studies to produce large improvements in prediction results.However,many of the previous efforts were limited to aggregating the information given by neighboring nodes and did not take advantage of the information provided by the edges represented by relations.To address the problem,Coupling Relation Strength with Graph Convolutional Networks(RS-GCN)is proposed,which is a model with an encoder-decoder framework to realize the embedding of entities and relations in the vector space.On the encoder side,RS-GCN captures graph structure and neighborhood information while aggregating the information given by neighboring nodes.On the decoder side,RotatE is utilized to model and infer various relational patterns.The models are evaluated on standard FB15k,WN18,FB15k-237 and WN18RR datasets,and the experiments show that RS-GCN achieves better results than the current state-of-the-art classical models on the above knowledge graph datasets.展开更多
事实核查是指基于证据文本的虚假信息检测任务,目前已有的研究方法主要是将声明文本与证据文本拼接后输入预训练模型进行分类判断,或者通过单一节点的全连接图进行推理判断。这些方法忽略了证据文本间的远距离语义关联和其包含的噪声干...事实核查是指基于证据文本的虚假信息检测任务,目前已有的研究方法主要是将声明文本与证据文本拼接后输入预训练模型进行分类判断,或者通过单一节点的全连接图进行推理判断。这些方法忽略了证据文本间的远距离语义关联和其包含的噪声干扰。针对以上问题,该文提出了一种基于跨证据文本实体关系的图卷积神经网络模型(C ross-E vidence Entity R elation Reasoning M odel,CERM)。该模型以多个证据文本的实体共现关系为基础,聚合不同实体对象的语义结构信息,同时减小噪声信息干扰,有效提升模型的虚假信息判别能力。实验结果证明,在公开数据集上该文提出的方法在通用评测指标上均优于现有的对比模型,验证了CERM模型在事实核查研究任务上的有效性。展开更多
远程监督关系抽取通过自动对齐自然语言文本与知识库生成带有标签的训练数据集,解决样本人工标注的问题。目前的远程监督研究大多没有关注到长尾(long-tail)数据,因此远程监督得到的大多数句包中所含句子太少,不能真实全面地反映数据的...远程监督关系抽取通过自动对齐自然语言文本与知识库生成带有标签的训练数据集,解决样本人工标注的问题。目前的远程监督研究大多没有关注到长尾(long-tail)数据,因此远程监督得到的大多数句包中所含句子太少,不能真实全面地反映数据的情况。因此,提出基于位置-类型注意力机制和图卷积网络的远程监督关系抽取模型PG+PTATT。利用图卷积网络GCN聚合相似句包的隐含高阶特征,并对句包进行优化以此得到句包更丰富全面的特征信息;同时构建位置-类型注意力机制PTATT,以解决远程监督关系抽取中错误标签的问题。PTATT利用实体词与非实体词的位置关系以及类型关系进行建模,减少噪声词带来的影响。提出的模型在New York Times数据集上进行实验验证,实验结果表明提出的模型能够有效解决远程监督关系抽取中存在的问题;同时,能够有效提升关系抽取的正确率。展开更多
文摘Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,sentiment analysis and question-answering systems.However,previous studies ignored much unusedstructural information in sentences that could enhance the performance of the relation extraction task.Moreover,most existing dependency-based models utilize self-attention to distinguish the importance of context,whichhardly deals withmultiple-structure information.To efficiently leverage multiple structure information,this paperproposes a dynamic structure attention mechanism model based on textual structure information,which deeplyintegrates word embedding,named entity recognition labels,part of speech,dependency tree and dependency typeinto a graph convolutional network.Specifically,our model extracts text features of different structures from theinput sentence.Textual Structure information Graph Convolutional Networks employs the dynamic structureattention mechanism to learn multi-structure attention,effectively distinguishing important contextual features invarious structural information.In addition,multi-structure weights are carefully designed as amergingmechanismin the different structure attention to dynamically adjust the final attention.This paper combines these featuresand trains a graph convolutional network for relation extraction.We experiment on supervised relation extractiondatasets including SemEval 2010 Task 8,TACRED,TACREV,and Re-TACED,the result significantly outperformsthe previous.
文摘In the link prediction task of knowledge graph completion,Graph Neural Network(GNN)-based knowledge graph completion models have been shown by previous studies to produce large improvements in prediction results.However,many of the previous efforts were limited to aggregating the information given by neighboring nodes and did not take advantage of the information provided by the edges represented by relations.To address the problem,Coupling Relation Strength with Graph Convolutional Networks(RS-GCN)is proposed,which is a model with an encoder-decoder framework to realize the embedding of entities and relations in the vector space.On the encoder side,RS-GCN captures graph structure and neighborhood information while aggregating the information given by neighboring nodes.On the decoder side,RotatE is utilized to model and infer various relational patterns.The models are evaluated on standard FB15k,WN18,FB15k-237 and WN18RR datasets,and the experiments show that RS-GCN achieves better results than the current state-of-the-art classical models on the above knowledge graph datasets.
文摘事实核查是指基于证据文本的虚假信息检测任务,目前已有的研究方法主要是将声明文本与证据文本拼接后输入预训练模型进行分类判断,或者通过单一节点的全连接图进行推理判断。这些方法忽略了证据文本间的远距离语义关联和其包含的噪声干扰。针对以上问题,该文提出了一种基于跨证据文本实体关系的图卷积神经网络模型(C ross-E vidence Entity R elation Reasoning M odel,CERM)。该模型以多个证据文本的实体共现关系为基础,聚合不同实体对象的语义结构信息,同时减小噪声信息干扰,有效提升模型的虚假信息判别能力。实验结果证明,在公开数据集上该文提出的方法在通用评测指标上均优于现有的对比模型,验证了CERM模型在事实核查研究任务上的有效性。
文摘远程监督关系抽取通过自动对齐自然语言文本与知识库生成带有标签的训练数据集,解决样本人工标注的问题。目前的远程监督研究大多没有关注到长尾(long-tail)数据,因此远程监督得到的大多数句包中所含句子太少,不能真实全面地反映数据的情况。因此,提出基于位置-类型注意力机制和图卷积网络的远程监督关系抽取模型PG+PTATT。利用图卷积网络GCN聚合相似句包的隐含高阶特征,并对句包进行优化以此得到句包更丰富全面的特征信息;同时构建位置-类型注意力机制PTATT,以解决远程监督关系抽取中错误标签的问题。PTATT利用实体词与非实体词的位置关系以及类型关系进行建模,减少噪声词带来的影响。提出的模型在New York Times数据集上进行实验验证,实验结果表明提出的模型能够有效解决远程监督关系抽取中存在的问题;同时,能够有效提升关系抽取的正确率。
