KBQA: constructing structured query graph from keyword query for semantic search

It is often very difficult to locate information on the Web because of its large and rapidly increasing amount of data. One key reason for this is traditional keyword-based search engines focus only on the resources whose title or content exactly matches the query keywords. People usually want to find the best matching resource itself to their query, not the documents which contain the resource. Recently, one promising way to meet this kind of requirement must be ontology-based approach for semantic search. However, it is also obvious there is still non-negligible gap between average users and ontological approach. To overcome this limitation of ontological approach such as Semantic Web, it is essential to provide an efficient method to fill the gap while taking full advantage of semantic technologies. To this end, we devise a method to generate alternative SPARQL queries from the typical natural language based query to the conventional search engines and evaluate the most matched SPARQL query among the alternatives by considering the characteristics of the target knowledge bases. We then implement a prototype system to evaluate the proposed method and validate its empirical performance and accuracy.