OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding

Semantic embedding has been widely investigated for aligning knowledge graph (KG) entities. Current methods have explored and utilized the graph structure, the entity names, and attributes, but ignore the ontology (or ontological schema) which contains critical meta information such as classes and their membership relationships with entities. In this paper, we propose an ontology-guided entity alignment method named OntoEA, where both KGs and their ontologies are jointly embedded, and the class hierarchy and the class disjointness are utilized to avoid false mappings. Extensive experiments on seven public and industrial benchmarks have demonstrated the state-ofthe-art performance of OntoEA and the effectiveness of the ontologies.

[1]  Jens Lehmann,et al.  DBpedia: A Nucleus for a Web of Open Data , 2007, ISWC/ASWC.

[2]  Wei Hu,et al.  Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation , 2019, AAAI.

[3]  Li Guo,et al.  Learning Knowledge Embeddings by Combining Limit-based Scoring Loss , 2017, CIKM.

[4]  Wei Hu,et al.  Bootstrapping Entity Alignment with Knowledge Graph Embedding , 2018, IJCAI.

[5]  Ian Horrocks,et al.  Large-scale Interactive Ontology Matching: Algorithms and Implementation , 2012, ECAI.

[6]  Yuting Wu,et al.  Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs , 2019, IJCAI.

[7]  Serge Abiteboul,et al.  PARIS: Probabilistic Alignment of Relations, Instances, and Schema , 2011, Proc. VLDB Endow..

[8]  Guillaume Lample,et al.  Word Translation Without Parallel Data , 2017, ICLR.

[9]  Jiaoyan Chen,et al.  Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding , 2021, IJCAI.

[10]  Wei Hu,et al.  Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs , 2019, ICML.

[11]  Ian Horrocks,et al.  OWL2Vec*: embedding of OWL ontologies , 2020, Machine Learning.

[12]  Zhichun Wang,et al.  Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks , 2018, EMNLP.

[13]  Steffen Staab,et al.  Knowledge graphs , 2021, Commun. ACM.

[14]  Carlo Zaniolo,et al.  Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment , 2016, IJCAI.

[15]  Zhiyuan Liu,et al.  Differentiating Concepts and Instances for Knowledge Graph Embedding , 2018, EMNLP.

[16]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[17]  Yizhou Sun,et al.  Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts , 2019, KDD.

[18]  Wei Hu,et al.  Recurrent Skipping Networks for Entity Alignment , 2018, ArXiv.

[19]  Wei Hu,et al.  Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding , 2017, SEMWEB.

[20]  Jiaoyan Chen,et al.  An Industry Evaluation of Embedding-based Entity Alignment , 2020, COLING.

[21]  Lu Yu,et al.  Semi-Supervised Entity Alignment via Knowledge Graph Embedding with Awareness of Degree Difference , 2019, WWW.

[22]  Andreas Abecker,et al.  Ontologies and the Semantic Web , 2011, Handbook of Semantic Web Technologies.

[23]  Rui Zhang,et al.  Entity Alignment between Knowledge Graphs Using Attribute Embeddings , 2019, AAAI.

[24]  Yuzhong Qu,et al.  Multi-view Knowledge Graph Embedding for Entity Alignment , 2019, IJCAI.

[25]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[26]  Ian Horrocks,et al.  Augmenting Ontology Alignment by Semantic Embedding and Distant Supervision , 2021, ESWC.

[27]  Markus Krötzsch,et al.  Wikidata , 2014, Commun. ACM.

[28]  Jianfeng Gao,et al.  Embedding Entities and Relations for Learning and Inference in Knowledge Bases , 2014, ICLR.

[29]  Chengkai Li,et al.  A benchmarking study of embedding-based entity alignment for knowledge graphs , 2020, Proc. VLDB Endow..

[30]  Martin Giese,et al.  Frequency-Based vs. Knowledge-Based Similarity Measures for Categorical Data , 2020, AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering.