信息工程大学学报2024，Vol.25Issue(3)：272-277,6.DOI:10.3969/j.issn.1671-0673.2024.03.004
针对长距离实体的双图路径推理模型
Double Graph Path Inference Model for Long-Distance Entities
摘要
Abstract
The entities relation between sentences in documents are often not directly obtainable.Ex-isting approaches usually use syntactic knowledge and co-reference,adjacency,co-occurrence,etc.to construct documents as the document graph and capture the interactions between entities.However,the large number and types of graph nodes and graph edges greatly limit the inference ability of the model.A bi-graph model with a simple structure and better inference effect is proposed in this paper.Firstly,heuristic rules are used to extract mention interactions and evidence sentences,and based on this,the mention graph and entity graph based on evidence sentences are constructed.Secondly,the at-tention mechanism is utilized to capture the inference paths between entity nodes in the entity graph.Finally,according to the inference paths,a suitable scoring function is used to predict entity relation-ship facts.Experiments on DocRED show that the model proposed in this paper achieves good results.关键词
文档级关系抽取/图神经网络/注意力机制Key words
document-level relation extraction/graph neural network/attention mechanism分类
信息技术与安全科学引用本文复制引用
祝涛杰,卢记仓,周刚,皮乾坤,丁肖摇..针对长距离实体的双图路径推理模型[J].信息工程大学学报,2024,25(3):272-277,6.基金项目
河南省自然科学基金(222300420590) （222300420590）
