ABSTRACT
Knowledge graph embedding maps entities and relationships of the graph into low dimensional dense vectors to expresse the semantic information, meantime provides effective support for downstream tasks such as link prediction. However, the existing knowledge graph embedding methods mainly focus on the explicit structured information in the graph and rarely use the entailed rich ontological knowledge. Therefore in the paper, a method for injecting ontology information into the embedding model is proposed, ontology information including class hierarchy information and relationship attribute constraints,especially symmetry attributes are considerd. By taking ontology information as extra constraints, the loss function is further refined.the generation of training samples is optimized and the number of false negative samples is limited. Experiments on the two datasets of DBpedia15K and NELL show that the embedding model can be further optimized by injecting ontology information. Specially, the hit rate of triple prediction is 63.70% for the no-type, and for type-triples the MR and the H@10 are 13.51 and 96.59% respectively. The proposed model has better performance than the basic model, which further confirms the effectiveness of the prior knowledge of ontology in knowledge graph embedding learning.
- [1]Feng X, Liu Q, Liu X. Intelligent Question Answering System Based on Knowledge Graph[C]. IEEE, 2021: 1515-1520.Google Scholar
- [2]GUO Q, ZHUANG F, QIN C, et al. A Survey on Knowledge Graph-Based Recommender Systems[J/OL]. IEEE Transactions on Knowledge and Data Engineering, 2020: 1-1. DOI:10.1109/TKDE.2020.3028705.Google ScholarCross Ref
- [3]Hou M, Wei R, Lu L, et al. A review of knowledge graph research and its application in the medical field[J]. Computer Research and Development, 2018, 55(12): 2585-2599.Google Scholar
- [4]AUER S, BIZER C, KOBILAROV G, et al. DBpedia: A Nucleus for a Web of Open Data[C]// Proceedings of the the International Semantic Web Conference. 2007: 722-735Google Scholar
- [5]SUCHANEK F M, KASNECI G, WEIKUM G. Yago: a core of semantic knowledge[C]//Proceedings of the 16th international conference on World Wide Web. 2007: 697-706.Google Scholar
- [6]CARLSON A, BETTERIDGE J, KISIEL B, et al. Toward an Architecture for Never-Ending Language Learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2010, 24(1): 1306-1313.Google Scholar
- [7]CHEN Z, WANG Y, ZHAO B, et al. Knowledge Graph Completion: A Review[J]. IEEE Access, 2020, 8: 192435-192456.Google ScholarCross Ref
- [8]ROSSI A, BARBOSA D, FIRMANI D, et al. Knowledge Graph Embedding for Link Prediction: A Comparative Analysis[J]. ACM Transactions on Knowledge Discovery from Data, 2021, 15(2): 1-49.Google ScholarDigital Library
- [9]LIN Y, LIU Z, SUN M, et al. Learning Entity and Relation Embeddings for Knowledge Graph Completion[C]//Proceedings of 29th AAAI Conference on Artificial Intelligence.2015.Google Scholar
- [10]JI S, PAN S, CAMBRIA E, et al. A Survey on Knowledge Graphs: Representation, Acquisition, and Applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(2): 494-514.Google ScholarCross Ref
- [11]HAO J, CHEN M, YU W, et al. Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019: 1709-1719.Google Scholar
- [12]LI Z, LIU X, WANG X, et al. TransO: a knowledge-driven representation learning method with ontology information constraints[J]. World Wide Web, 2023, 26(1): 297-319.Google ScholarDigital Library
- [13]D’AMATO C, QUATRARO N F, FANIZZI N. Injecting Background Knowledge into Embedding Models for Predictive Tasks on Knowledge Graphs[C]. //Proceedings of the Extended Semantic Web Conference 2021: 441-457.Google Scholar
- [14]HITZLER P, KRÖTZSCH M, RUDOLPH S. Foundations of Semantic Web technologies[M]. Boca Raton: CRC Press, 2010.Google Scholar
- [15]BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating Embeddings for Modeling Multi-relational Data[C]. Proceedings of the Advances in Neural Information Processing Systems. 2013, 26.Google Scholar
- [16]WANG Z, ZHANG J, FENG J, et al. Knowledge Graph Embedding by Translating on Hyperplanes[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2014, 28(1).Google Scholar
- [17]JI G, HE S, XU L, et al. Knowledge Graph Embedding via Dynamic Mapping Matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 2015: 687-696.Google Scholar
- [18]WANG Y, WANG H, HE J, et al. TAGAT: Type-Aware Graph Attention neTworks for reasoning over knowledge graphs[J]. Knowledge-Based Systems, 2021, 233: 107500.Google ScholarDigital Library
- [19]ROSSO P, YANG D, OSTAPUK N, et al. RETA: A Schema-Aware, End-to-End Solution for Instance Completion in Knowledge Graphs[C]//Proceedings of the Web Conference,2021: 845-856.Google Scholar
- [20]ZHANG W. Knowledge Graph Embedding with Diversity of Structures[C]//Proceedings of the 26th International Conference on World Wide Web 2017: 747-753.Google Scholar
- [21]TROUILLON T, WELBL J, RIEDEL S, et al. Complex Embeddings for Simple Link Prediction[M/OL]. arXiv, 2016[2023-06-29].Google Scholar
- [22]Shaojie Li, Yong Liu. Towards Sharper Generalization Bounds for Structured Prediction. In Advances in Neural Information Processing Systems (NeurIPS), 2021.Google Scholar
- [23]Changlong Wang,Zhiyong Feng,XiaoWang Zhang,Xin Wang, Guozheng Rao,Daoxun fu. ComR: A combined OWL reasoner for ontology classification, Frontiers of Computer Science, 2019, 13(1):139-156.Google ScholarDigital Library
Index Terms
- An Ontology-enhanced Knowledge Graph Embedding Method
Recommendations
TransO: a knowledge-driven representation learning method with ontology information constraints
AbstractRepresentation learning techniques for knowledge graphs (KGs) are crucial for constructing knowledge-driven decisions in complex network data application scenarios. Most existing methods focus mainly on structured information, ignoring the ...
Formal semantics-preserving translation from fuzzy ER model to fuzzy OWL DL ontology
Ontology is an important part of the W3C standards for the Semantic Web, and how to quickly and cheaply construct Web ontologies has become a key technology to enable the Semantic Web. However, information imprecision and uncertainty exist in many real-...
Knowledge representation and reasoning of XML with ontology
SAC '11: Proceedings of the 2011 ACM Symposium on Applied ComputingToday XML has reached a wide acceptance as the data exchange format for e-commerce. Unfortunately, XML covers the syntactic level, but lacks semantics. Ontology can represent shared domain knowledge and enable semantic interoperability. Therefore, in ...
Comments