A domain knowledge graph construction method based on Wikipedia

Abstract

In order to achieve real-time updating of the domain knowledge graph and improve the relationship extraction ability in the construction process, a domain knowledge graph construction method is proposed. Based on the structured knowledge in Wikipedia’s classification system, we acquire concepts and instances contained in subject areas. A relationship extraction algorithm based on co-word analysis is intended to extract the classification relationships in semi-structured open labels. A Bi-GRU remote supervised relationship extraction model based on a multiple-scale attention mechanism and an improved cross-entropy loss function is proposed to obtain the non-classification relationships of concepts in unstructured texts. Experiments show that the proposed model performs better than the existing methods. Based on the obtained concepts, instances and relationships, a domain knowledge graph is constructed and the domain-independent nodes and relationships contained in them are removed through a vector variance algorithm. The effectiveness of the proposed method is verified by constructing a food domain knowledge graph based on Wikipedia.