Paper Info
Title
RDF shape induction using knowledge base profiling.
Abstract
Knowledge Graphs (KGs) are becoming the core of most artificial intelligent and cognitive applications. Popular KGs such as DBpedia and Wikidata have chosen the RDF data model to represent their data. Despite the advantages, there are challenges in using RDF data, for example, data validation. Ontologies for specifying domain conceptualizations in RDF data are designed for entailments rather than validation. Most ontologies lack the granular information needed for validating constraints. Recent work on RDF Shapes and standardization of languages such as SHACL and ShEX provide better mechanisms for representing integrity constraints for RDF data. However, manually creating constraints for large KGs is still a tedious task. In this paper, we present a data driven approach for inducing integrity constraints for RDF data using data profiling. Those constraints can be combined into RDF Shapes and can be used to validate RDF graphs. Our method is based on machine learning techniques to automatically generate RDF shapes using profiled RDF data as features. In the experiments, the proposed approach achieved 97% precision in deriving RDF Shapes with cardinality constraints for a subset of DBpedia data.
Year
DOI
Venue
2018
10.1145/3167132.3167341
SAC 2018: Symposium on Applied Computing Pau France April, 2018
Keywords
Field
DocType
RDF Shape, Knowledge Base, Data Quality, Machine Learning
Ontology (information science),Data validation,Data-driven,Data quality,Information retrieval,Computer science,Data integrity,Data profiling,Data model,RDF
Conference
ISBN
Citations 
PageRank 
978-1-4503-5191-1
1
0.35
References 
Authors
12
6
Name
Order
Citations
PageRank
Nandana Mihindukulasooriya17517.75
Mohammad Rifat Ahmmad Rashid210.35
Giuseppe Rizzo334937.75
Raul Garcia-Castro452756.11
Óscar Corcho52194194.44
M. Torchiano6216.23