Automatic Semantic Modeling for Structural Data Source with the Prior Knowledge from Knowledge Base

TL;DR

This paper presents an automatic method for semantic modeling of structured data sources by leveraging prior knowledge from knowledge graphs, improving over existing solutions especially with limited known models.

Contribution

The paper introduces a novel approach combining machine learning, graph matching, and subgraph mining to automatically infer semantics and relationships in data sources using knowledge graphs.

Findings

Outperforms state-of-the-art solutions in limited-data scenarios

Effective in inferring attribute relationships automatically

Enhances semantic annotation accuracy for structured data

Abstract

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.