Naga

The presence of encyclopedic Web sources, such as Wikipedia, the Internet Movie (IMDB), World Factbook, etc. calls for new querying techniques that simple and yet more expressive than those provided by standard -based search engines. Searching for explicit knowledge needs to inherent semantic structures involving entities and relationships. this demonstration proposal, we describe a semantic search system named . NAGA operates on a knowledge graph, which contains millions of entities relationships derived from various encyclopedic Web sources, such as the above. NAGA's graph-based query language is geared towards expressing with additional semantic information. Its scoring model is based on the of generative language models, and formalizes several desiderata as confidence, informativeness and compactness of answers. propose a demonstration of NAGA which will allow users to browse the base through a user interface, enter queries in NAGA's query language tune the ranking parameters to test various ranking aspects.