Triple Trustworthiness Measurement for Knowledge Graph

被引:47
|
作者
Jia, Shengbin [1 ]
Xiang, Yang [1 ]
Chen, Xiaojun [1 ]
机构
[1] Tongji Univ, Shanghai, Peoples R China
基金
中国国家自然科学基金;
关键词
Knowledge graph; trustworthiness; neural network; error detection; NETWORKS; DBPEDIA; BASE;
D O I
10.1145/3308558.3313586
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
The Knowledge graph (KG) uses the triples to describe the facts in the real world. It has been widely used in intelligent analysis and applications. However, possible noises and conflicts are inevitably introduced in the process of constructing. And the KG based tasks or applications assume that the knowledge in the KG is completely correct and inevitably bring about potential deviations. In this paper, we establish a knowledge graph triple trustworthiness measurement model that quantify their semantic correctness and the true degree of the facts expressed. The model is a crisscrossing neural network structure. It synthesizes the internal semantic information in the triples and the global inference information of the KG to achieve the trustworthiness measurement and fusion in the three levels of entity level, relationship level, and KG global level. We analyzed the validity of the model output confidence values, and conducted experiments in the real-world dataset FB15K (from Freebase) for the knowledge graph error detection task. The experimental results showed that compared with other models, our model achieved significant and consistent improvements.
引用
收藏
页码:2865 / 2871
页数:7
相关论文
共 50 条
  • [1] Triple trustworthiness evaluation for knowledge graph of industrial domain
    Wang, Chu
    Wang, Jian
    [J]. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2023, 45 (02) : 2967 - 2977
  • [2] Trustworthiness Measurement for Multimedia Domain Knowledge Graph
    Yan, Yujie
    Yu, Peng
    Fang, Honglin
    Wu, Zihao
    [J]. 2022 IEEE INTERNATIONAL SYMPOSIUM ON BROADBAND MULTIMEDIA SYSTEMS AND BROADCASTING (BMSB), 2022,
  • [3] Triple confidence measurement in knowledge graph with multiple heterogeneous evidences
    Wu, Tianxing
    Yao, Kai
    Li, Wei
    Qi, Guilin
    Yu, Yijun
    Zhao, Nengwen
    Zhang, Renyou
    Duan, Peibo
    [J]. WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2024, 27 (06):
  • [4] Trustworthiness-aware knowledge graph representation for recommendation
    Ge, Yan
    Ma, Jun
    Zhang, Li
    Li, Xiang
    Lu, Haiping
    [J]. KNOWLEDGE-BASED SYSTEMS, 2023, 278
  • [5] PTrustE: A high-accuracy knowledge graph noise detection method based on path trustworthiness and triple embedding
    Ma, Jiangtao
    Zhou, Chenyu
    Wang, Yanjun
    Guo, Yifan
    Hu, Guangwu
    Qiao, Yaqiong
    Wang, Yong
    [J]. Knowledge-Based Systems, 2022, 256
  • [6] PTrustE: A high-accuracy knowledge graph noise detection method based on path trustworthiness and triple embedding
    Ma, Jiangtao
    Zhou, Chenyu
    Wang, Yanjun
    Guo, Yifan
    Hu, Guangwu
    Qiao, Yaqiong
    Wang, Yong
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 256
  • [7] Knowledge Graph Embedding with Triple Context
    Shi, Jun
    Gao, Huan
    Qi, Guilin
    Zhou, Zhangquan
    [J]. CIKM'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2017, : 2299 - 2302
  • [8] Triple Classification for Scholarly Knowledge Graph Completion
    Jaradeh, Mohamad Yaser
    Singh, Kuldeep
    Stocker, Markus
    Auer, Soeren
    [J]. PROCEEDINGS OF THE 11TH KNOWLEDGE CAPTURE CONFERENCE (K-CAP '21), 2021, : 225 - 232
  • [9] A Knowledge Graph Embedding Framework With Triple Semantics
    Wang, Yan
    Liang, Honghao
    Zheng, Kaihong
    Yang, Jingfeng
    Zeng, Lukun
    Gong, Qihang
    Li, Sheng
    Zhou, Shangli
    [J]. IEEE ACCESS, 2023, 11 : 35784 - 35795
  • [10] Knowledge Graph Completion with Triple Structure and Text Representation
    Shuang Liu
    YuFeng Qin
    Man Xu
    Simon Kolmanič
    [J]. International Journal of Computational Intelligence Systems, 16