摘要
关系抽取作为信息抽取的子任务,旨在从非结构化文本中抽取出便于处理的结构化知识,对于自动问答、知识图谱构建等下游任务至关重要。该文在文档级的关系抽取语料上开展工作,包括但不局限于传统的句子级关系抽取。为了解决文档级关系抽取中长距离依赖问题,并且对特征贡献度加以区分,该文将图卷积模型和多头注意力机制相融合构建了图注意力卷积模型。该模型通过多头注意力机制为同指、句法等信息构建的拓扑图构建动态拓扑图,然后使用图卷积模型和动态图捕获实体间的全局和局部依赖信息。该文分别在DocRED语料和自主扩展的ACE 2005语料上进行实验,与基准模型相比,基准模型上融入图注意力卷积的模型在两个数据集上的F;值分别提升了2.03%和3.93%,实验结果表明了该方法的有效性。
As a subtask of information extraction,relation extraction aims to extract the structured knowledge from unstructured text,which is very important for the downstream tasks such as automatic question answering and knowledge graph construction.Focused on document-level relation extraction,this paper proposed a graph attention convolution model to deal with long-distance dependence issue.The model uses a multi-head attention mechanism to construct a dynamic topological graph for coreference,syntax and other information.Then it uses the graph convolution model and dynamic graph to capture global and local dependency information between entities.Experiments on the DocRED corpus and the self-expanding ACE 2005 corpus comfirm improvements on F;values by 2.03 and 3.93,respectively.
作者
吴婷
孔芳
WU Ting;KONG Fang(School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China)
出处
《中文信息学报》
CSCD
北大核心
2021年第10期73-80,共8页
Journal of Chinese Information Processing
关键词
文档级关系抽取
图卷积网络
图注意力
document level relation extraction
graph convolution network
graph attention