A versatile approach for constructing a domain knowledge graph for culture

Abstract

[Question] The construction of cultural knowledge base in digital library is in progress with the development of information technology. However, traditional cultural knowledge bases are facing the problems of high participation of manual operation and monotonous data source. This paper combines knowledge graph, a frontier technology of artificial intelligence, to explore a new method of building high‐quality, automated cultural knowledge base. [Method] Using the experimental method, we selected the knowledge of the Hundred Schools of Thought in ancient China. Because these knowledges are clearly interrelated, it is suitable to construct the knowledge graph of them. The knowledge graph can provide experience for the construction of other cultural knowledge bases. [Conclusion] At present, this paper has preliminarily completed the experimental design of the knowledge graph of the Hundred Schools of Thought, and provided the flowchart of the construction of cultural domain knowledge graph.

Domain-specific knowledge graphs: A survey

“…The author constructed the KG employing Baidu Encyclopedia 17 as the knowledge source, BiLSTM-CRF for entity recognition, and DeepKE (developed by Zhejiang University) for relation inference. Constructing cultural knowledge bases that benefit from domain ontology and cultural KGs was elaborated further in [178][179][180].…”