Abstract
An increasingly huge amount of sport news published from a number of heterogeneous sources on the Web brings challenges to the traditional searching method using keywords. Providing an expressive way to retrieve news items and exploiting the advantages of semantic search technique in the development of Web-based sports news aggregation system is within our consideration. This paper presents a method to translate natural language questions into queries in SPARQL, the standard query language recommended by W3C for semantic data. Our contribution consists mainly of the construction of a semantic model representing a question, the detection of ontology vocabularies and knowledge base elements in question, and their mapping to generate a query. We evaluate the method based on a set of natural language questions and the results show that the proposed method achieves good performance with respect to precision.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
