Natural Language Interface for Querying Linked Data Using Case-Based Reasoning (original) (raw)
Indian Journal of Computer Science and Engineering
With the emergence of Linked Data in RDF format, query systems should execute structured queries in SPARQL. Still, only expert programmers can specify their information needs and cope with Linked Data sources' diversity and heterogeneity. Therefore, understanding Natural Language (NL) queries to construct correct SPARQL queries is a great challenge for these query systems to access multiple heterogeneous semantic sources and Linked Data sets. This paper presents a new approach for querying Linked Data with NL queries. Our method identifies the topic and search criteria of the NL query based on the Case-Based Reasoning (CBR) technique. Next, we match the identified topic and search criteria to their corresponding entities in the dataset. Then, we represent the query as triples based on the semantic relations provided by the dataset. Finally, our system executes the SPARQL queries generated from the query triples, based on the proposed generation rules, to query the dataset and retrieve the relevant answers. Experiments showed that the proposed approach is efficient compared to the existing systems in terms of precision and recall.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.