Approximate Reasoning for Large-Scale ABox in OWL DL Based on Neural-Symbolic Learning

被引:1
作者
Zhu, Xixi [1 ]
Liu, Bin [1 ]
Zhu, Cheng [1 ]
Ding, Zhaoyun [1 ]
Yao, Li [1 ]
机构
[1] Natl Univ Def Technol, Sci & Technol Informat Syst & Engn Lab, Changsha 410073, Peoples R China
基金
美国国家科学基金会;
关键词
neural-symbolic learning; approximate reasoning; large-scale ABox reasoning; neural network; ontology reasoning; OWL DL; NETWORKS;
D O I
10.3390/math11030495
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
The ontology knowledge base (KB) can be divided into two parts: TBox and ABox, where the former models schema-level knowledge within the domain, and the latter is a set of statements of assertions or facts about instances. ABox reasoning is a process of discovering implicit knowledge in ABox based on the existing KB, which is of great value in KB applications. ABox reasoning is influenced by both the complexity of TBox and scale of ABox. The traditional logic-based ontology reasoning methods are usually designed to be provably sound and complete but suffer from long algorithm runtimes and do not scale well for ontology KB represented by OWL DL (Description Logic). In some application scenarios, the soundness and completeness of reasoning results are not the key constraints, and it is acceptable to sacrifice them in exchange for the improvement of reasoning efficiency to some extent. Based on this view, an approximate reasoning method for large-scale ABox in OWL DL KBs was proposed, which is named the ChunfyReasoner (CFR). The CFR introduces neural-symbolic learning into ABox reasoning and integrates the advantages of symbolic systems and neural networks (NNs). By training the NN model, the CFR approximately compiles the logic deduction process of ontology reasoning, which can greatly improve the reasoning speed while ensuring higher reasoning quality. In this paper, we state the basic idea, framework, and construction process of the CFR in detail, and we conduct experiments on two open-source ontologies built on OWL DL. The experimental results verify the effectiveness of our method and show that the CFR can support the applications of large-scale ABox reasoning of OWL DL KBs.
引用
收藏
页数:24
相关论文
共 50 条
  • [1] Advanced metaheuristic optimization techniques in applications of deep neural networks: a review
    Abd Elaziz, Mohamed
    Dahou, Abdelghani
    Abualigah, Laith
    Yu, Liyang
    Alshinwan, Mohammad
    Khasawneh, Ahmad M.
    Lu, Songfeng
    [J]. NEURAL COMPUTING & APPLICATIONS, 2021, 33 (21) : 14079 - 14099
  • [2] Domain-specific knowledge graphs: A survey
    Abu-Salih, Bilal
    [J]. JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 2021, 185
  • [3] Neuro-symbolic representation learning on biological knowledge graphs
    Alshahrani, Mona
    Khan, Mohammad Asif
    Maddouri, Omar
    Kinjo, Akira R.
    Queralt-Rosinach, Nuria
    Hoehndorf, Robert
    [J]. BIOINFORMATICS, 2017, 33 (17) : 2723 - 2730
  • [4] Baader F, 2003, IN HAND I S, P3
  • [5] Belle Vaishak, 2020, Scalable Uncertainty Management. 14th International Conference, SUM 2020. Proceedings. Lecture Notes in Artificial Intelligence Subseries of Lecture Notes in Computer Science (LNAI 12322), P3, DOI 10.1007/978-3-030-58449-8_1
  • [6] Besold TR, 2022, FRONT ARTIF INTEL AP, V342, P1, DOI 10.3233/FAIA210348
  • [7] Bordes A., 2013, ADV NEURAL INFORM PR, P2787
  • [8] Cardoso J, 2006, SEMANTIC WEB BEYOND, V3, P3, DOI 10.1007/978-0-387-34685-4_1
  • [9] Che FH, 2020, AAAI CONF ARTIF INTE, V34, P2774
  • [10] Knowledge Graph Completion: A Review
    Chen, Zhe
    Wang, Yuehan
    Zhao, Bin
    Cheng, Jing
    Zhao, Xin
    Duan, Zongtao
    [J]. IEEE ACCESS, 2020, 8 (08): : 192435 - 192456