摘要
实体对齐(EA)的目标是从多个知识图谱(KG)中识别等价的实体对,并构建一个更全面、统一的知识图谱.大多数EA方法主要关注KG的结构模式,缺乏对多模态信息的探索.已有的一些多模态EA方法在这个领域做出了良好的尝试.但是,它们存在两个缺点:(1)针对不同模态信息采用复杂且不同的建模方式,导致模态建模不一致且建模低效;(2)由于EA中各模态间的异质性,模态融合效果往往不佳.为了解决这些挑战,该文提出了 PathFusion,使用模态相似性路径作为信息载体,有效地合并来自不同模态的信息.在真实世界的数据集上的实验结果显示,与最先进的方法相比,PathFusion在Hits@1上提高了 22.4％～28.9％,在MRR上提高了 0.194～0.245,验证了 PathFusion的优越性.
Abstract
The objective of Entity Alignment(EA)is to identify equivalent entity pairs from multiple Knowledge Graphs(KGs)and create a more comprehensive and unified KG.The majority of EA methods have primarily fo-cused on the structural modality of KGs,lacking exploration of multi-modal information.A few multi-modal EA methods have made good attempts in this field.Still,they have two shortcomings:(1)inconsistent and inefficient modality modeling that designs complex and distinct models for each modality;(2)ineffective modality fusion due to the heterogeneous nature of modalities in EA.To tackle these challenges,we propose PathFusion,which effec-tively combines information from different modalities using the path as an information carrier.Experimental results on real-world datasets demonstrate the superiority of PathFusion over state-of-the-art methods,with 22.4％～28.9％absolute improvement on Hits@1,and 0.194～0.245 absolute improvement on MRR.
维普
万方数据