Finding Similar Entities Across Knowledge Graphs

Abstract

Finding similar entities among knowledge graphs is an essential research problem for knowledge integration and knowledge graph connection. This paper aims at finding semantically similar entities between two knowledge graphs. This can help end users and search agents more effectively and easily access pertinent information across knowledge graphs. Given a query entity in one knowledge graph, the proposed approach tries to find the most similar entity in another knowledge graph. The main idea is to leverage graph embedding, clustering, regression and sentence embedding. In this approach, RDF2Vec has been employed to generate vector representations of all entities of the second knowledge graph and then the vectors have been clustered based on cosine similarity using K medoids algorithm. Then, an artificial neural network with multilayer perception topology has been used as a regression model to predict the corresponding vector in the second knowledge graph for a given vector from the first knowledge graph. After determining the cluster of the predicated vector, the entities of the detected cluster are ranked through sentence-BERT method and finally the entity with the highest rank is chosen as the most similar one. To evaluate the proposed approach, experiments have been conducted on real-world knowledge graphs. The experimental results demonstrate the effectiveness of the proposed approach.

Interactive Search on the Web: The Story So Far

“…Knowledge base construction: It summarizes methods, such as schema alignment, entity matching, and entity fusion, for integrating knowledge into a knowledge base. For instance, to detect duplicates (i.e., entity matching), it is necessary to compare every entity with each other, which is not recommendable for large knowledge bases [61,62]. In this case, indexing techniques might help to reduce the number of comparison, e.g., some indexing approaches are: an ontology-based index [63] that stores the ontology graph, an entity-based index that takes into account the relationships between entities, and a textual-based index that considers triples (subject, predicate, object).…”