Ontology-Based Translation of Natural Language Queries to SPARQL

We present an implemented approach to transform natu-ral language sentences into SPARQL, using background knowledge from ontologies and lexicons. Therefore, el-igible technologies and data storage possibilities are an-alyzed and evaluated. The contributions of this paper are twofold. Firstly, we describe the motivation and current needs for a natural language access to industry data. We describe several scenarios where the proposed solution is required. Resulting in an architectural approach based on automatic SPARQL query construction for effective natural language queries. Secondly, we analyze the per-formance of RDBMS, RDF and Triple Stores for the knowledge representation. The proposed approach will be evaluated on the basis of a query catalog by means of query efficiency, accuracy, and data storage perfor-mance. The results show, that natural language access to industry data using ontologies and lexicons, is a sim-ple but effective approach to improve the diagnosis pro-cess and the data search for a broad range of users. Fur-thermore, virtual RDF graphs do support the DB-driven knowledge graph representation process, but do not per-form efficient under industry conditions in terms of per-formance and scalability