Translating Natural Language Questions into CIDOC-CRM SPARQL Queries to Access Cultural Heritage Knowledge Bases

Abstract

To explore information on the semantic web, SPARQL queries or DL-queries are suitable tools. However, users interested in exploring the content of such knowledge bases often find it challenging to employ formal query languages, as this requires familiarity with the target domain’s representation model. To address these challenges, a question-answering system that automatically translates natural language questions into SPARQL queries, over the Smithsonian American Art Museum CIDOC-CRM representation is presented. The proposed approach uses an ontology, named Query Ontology, defined to represent the natural language concepts and relations specific to the question’s domain. This system’s architecture uses a traditional natural language processing symbolic approach, with a pipeline of modules for the syntactic, semantic, and pragmatic analysis. An evaluation of the proposed system is presented and shows very promising results.