arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.05596cs.CLcs.AIcs.LG
收藏

基于概率推理和语义嵌入的无监督知识图谱对齐

Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding

Tencent Jarvis Lab(腾讯天衍实验室);University of Oxford(牛津大学);Tencent(腾讯);Zhejiang University(浙江大学)

Zhiyuan Qi, Ziheng Zhang, Jiaoyan Chen, Xi Chen, Yuejia Xiang, Ningyu Zhang, Yefeng Zheng

摘要:

知识图谱(KG)对齐是为了发现映射(即,等同实体、关系和其他)。现有的方法可以分为基于嵌入的模型和传统的基于推理和词汇匹配的系统。前者通过跨KG嵌入计算实体的相似性,但它们通常依赖于理想的监督学习设置以获得良好的性能,并且缺乏适当的推理以避免逻辑错误的映射;而后者解决了推理问题,但在利用KG图结构和实体上下文方面很差。在这项研究中,我们的目标是结合上述两个解决方案,从而提出了一个迭代框架命名为PRASE,这是基于概率推理和语义嵌入。它从概率推理系统PARIS中通过实体映射学习KG嵌入,并将得到的实体映射和嵌入反馈回PARIS进行增强。PRASE框架与不同的基于嵌入的模型兼容,我们在多个数据集上的实验证明了其最先进的性能。

英文摘要:

Knowledge Graph (KG) alignment is to discover the mappings (i.e., equivalent entities, relations, and others) between two KGs. The existing methods can be divided into the embedding-based models, and the conventional reasoning and lexical matching based systems. The former compute the similarity of entities via their cross-KG embeddings, but they usually rely on an ideal supervised learning setting for good performance and lack appropriate reasoning to avoid logically wrong mappings; while the latter address the reasoning issue but are poor at utilizing the KG graph structures and the entity contexts. In this study, we aim at combining the above two solutions and thus propose an iterative framework named PRASE which is based on probabilistic reasoning and semantic embedding. It learns the KG embeddings via entity mappings from a probabilistic reasoning system named PARIS, and feeds the resultant entity mappings and embeddings back into PARIS for augmentation. The PRASE framework is compatible with different embedding-based models, and our experiments on multiple datasets have demonstrated its state-of-the-art performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑