徽派建筑知识图谱的半自动化构建

Semi-automated Build of Huizhou Architectural Knowledge Graph

本文针对徽派建筑数据异构多源和非结构化的特点,提出一种BiLSTM-CRF模型与徽派建筑词典相结合的命名实体识别方法,利用先验知识的辅助作用,提升实体识别效果,完成对建筑实体进行的识别抽取。利用Neo4j图数据库存储知识,用属性图模型表示知识。最后使用Neo4j图数据库对构建的徽派建筑知识图谱进行了可视化展示。研究结果表明,此方法能够有效地构建徽派建筑领域知识图谱,为今后徽派建筑知识智能化推荐和搜索系统研究奠定基础。

Considering heterogeneous multiple sources and unstructured characteristics of Huizhou architecture data,a named entity recognition method combining BiLSTM-CRF model and Huizhou architecture lexicon is proposed in this paper to improve the entity recognition with prior knowledge.The Neo4j graph database is used to store knowledge and the attribute graph model to represent,hence the authors visualize Huizhou architectural knowledge graph.The results show that this method can build a knowledge graph in the field of Huizhou architecture effectively,which lays a foundation for further research on intelligent recommendation and search systems of Huizhou architecture knowledge.