MMOY: Towards deriving a metallic materials ontology from Yago

In recent years, materials informatics has been getting more and more attention, and knowledge base plays a critical role for intelligent applications of materials science and engineering. The emerged materials ontologies, most of which are designed manually, provide useful but relatively limited materials knowledge. In contrast, Linked Open Data (LOD) provides some huge open knowledge bases in which lots of materials knowledge is hidden. Therefore, we try to derive an ontology about metallic materials domain from Yago which is a well-known open knowledge base. In this paper, an approach is proposed to generate metallic materials ontology based on the structure of Yago and string matching algorithm. First, we define keywords to initially obtain some metallic materials concepts from Yago by string matching algorithm. Then, based on these obtained concepts, the metallic materials knowledge and related knowledge is extracted according to the structural features of Yago, so as to acquire a metallic materials ontology (named MMOY). The detailed extraction strategy is elaborated as a set of logic rules designed for our approach. The approach is evaluated in light of F1-measure and time performance, and the experimental results demonstrate that the proposed approach can extract metallic materials knowledge and related knowledge from Yago effectively, and the time performance is acceptable. In addition, we have developed a prototype system to visually demonstrate the knowledge structure of MMOY.