Automatic Semantic Modeling for Structural Data Source with the Prior Knowledge from Knowledge Base
This addresses the challenge of automating semantic modeling for data sharing, reducing manual effort and expertise required, though it appears incremental as it builds on existing annotation work.
The paper tackles the Relational-To-Ontology Mapping Problem by proposing an automatic method to semantically annotate structured data sources, using machine learning and graph techniques with knowledge graphs as prior knowledge; it outperforms state-of-the-art solutions in tricky cases with few known semantic models.
A critical step in sharing semantic content online is to map the structural data source to a public domain ontology. This problem is denoted as the Relational-To-Ontology Mapping Problem (Rel2Onto). A huge effort and expertise are required for manually modeling the semantics of data. Therefore, an automatic approach for learning the semantics of a data source is desirable. Most of the existing work studies the semantic annotation of source attributes. However, although critical, the research for automatically inferring the relationships between attributes is very limited. In this paper, we propose a novel method for semantically annotating structured data sources using machine learning, graph matching and modified frequent subgraph mining to amend the candidate model. In our work, Knowledge graph is used as prior knowledge. Our evaluation shows that our approach outperforms two state-of-the-art solutions in tricky cases where only a few semantic models are known.