摘要
针对知识图谱实体对齐任务中缺乏训练数据以及长尾实体对齐准确率较低的问题,提出一种基于自适应特征融合策略的迭代实体对齐方法,并设计一种迭代策略自动扩充训练数据的规模.该方法使用知识图谱的结构信息,并利用关系、属性和实体名称信息作为语义信息辅助对齐,从而提升对齐效果.在数据集上的实验结果表明,该模型在知识图谱实体对齐任务中效果良好.
Aiming at the problems of insufficient training data and low accuracy of long-tail entity alignment in the task of knowledge graph entity alignment,we proposed an iterative entity alignment method based on an adaptive feature fusion strategy and designed an iterative strategy to automatically expand the scale of the training data.This method utilized the structural information of the knowledge graph and utilized relationships,attributes,and entity name information as semantic information to assist alignment and improve alignment effectiveness.The experimental results on the dataset show that the proposed model performs well in the task of knowledge graph entity alignment.
作者
李婷婷
邵斐
温天晓
董飒
LI Tingting;SHAO Fei;WEN Tianxiao;DONG Sa(Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education,College of Computer Science and Technology,Jilin University,Changchun 130012,China)
出处
《吉林大学学报（理学版）》
CAS
北大核心
2024年第3期629-635,共7页
Journal of Jilin University:Science Edition
基金
吉林省科技发展计划项目(批准号:20230201083GX).
关键词
知识图谱
实体对齐
迭代策略
自适应特征融合
knowledge graph
entity alignment
iterative strategy
adaptive feature fusion
