Datensatz

Zusammenfassung

The Web has the potential to become the world's largest knowledge base. In order to unleash this potential, the wealth of information available on the web needs to be extracted and organized. There is a need for new querying techniques that are simple yet more expressive than those provided by standard keyword-based search engines. Search for knowledge rather than Web pages needs to consider inherent semantic structures like entities (person, organization, etc.) and relationships (isA,locatedIn, etc.). In this paper, we propose {NAGA}, a new semantic search engine. {NAGA}'s knowledge base, which is organized as a graph with typed edges, consists of millions of entities and relationships automatically extracted fromWeb-based corpora. A query language capable of expressing keyword search for the casual user as well as graph queries with regular expressions for the expert, enables the formulation of queries with additional semantic information. We introduce a novel scoring model, based on the principles of generative language models, which formalizes several notions like confidence, informativeness and compactness and uses them to rank query results. We demonstrate {NAGA}'s superior result quality over current search engines by conducting a comprehensive evaluation, including user assessments, for advanced queries.