Abstract
Semantic search extends the scope of conventional information search and retrieval paradigms from documentoriented and to entity and knowledge-centric search and retrieval. By attempting to provide direct and intuitive answers such systems alleviate information overload problem and reduce information seekers’ cognitive overhead. Ontologies and knowledge bases are fundamental cornerstones in semantic search systems based on which sophisticated search mechanisms and efficient search services are designed. Nevertheless, acquisition of quality knowledge from heterogeneous sources on the Web is never a trivial task. Transformation of data in existing databases seems a promising bootstrapping approach, while information providers may refuse to do so because of intellectual property issues. In this article we discuss issues related to knowledge acquisition for semantic search systems. In particular, we discuss ontology learning from unstructured text corpus, which is an automatic knowledge acquisition process using different techniques.