Enabling type/condition-specified entity/fact retrieval using semantic knowledge extracted from wikipedia

Abstract

Wikipedia has recently become an important semantic knowledge resource, thanks to its semi-structured semantic features and the huge amount of user-generated content covering a wide range of topics. The mode of information retrieval on Wikipedia, as on the Web in general, however, remains that of conventional keyword-based page/document retrieval. The project presented in this paper, entitled PanAnthropon FilmWorld, aims at demonstrating direct, sophisticated entity/fact retrieval by extracting/deriving semantic knowledge from Wikipedia and by representing facts using domain-relevant classes, entities, attributes, and categories. To this end, a semantic knowledge base containing the extracted data and a semantic search interface demonstrating the proposed retrieval capability have been constructed. The focus of this paper is on the details concerning semantic knowledge extraction and derivation. However, the interface is fully functional. The results of evaluation confirm both the quality of knowledge extraction and the effectiveness of entity/fact retrieval using the interface.