Semantic query graph based SPARQL generation from natural language questions

Shengli Song, Wen Huang, Yulong Sun

Abstract: In order to precisely represent natural language questions (NLQs) in question answering system (QAS) and provide a more naturally interactive mode, we require SPARQL, a formalized query patterns, instead of search expression to express the user’s semantic query intention. However, how to generate and evaluate SPARQL query from NLQ is a mostly open research question. In this paper, we propose a framework that can help users translating NLQ into well-formed queries for knowledge based systems. We define a new graph structure, semantic query graph, and vocabulary to match all kinds of complex and compound questions without using domain ontology. Through query expansion and semantic query graph generation, the framework resembles subgraphs of the knowledge base and can be directly mapped to a logical form. Extensive experiments over NLQ in real RDF QASs verify the feasibility and efficiency of semantic query graph and our proposed framework with average F-measure of 0.825.