Using Wikipedia categories for compact representations of chemical documents

摘要: Today, Web pages are usually accessed using text search engines, whereas documents stored in the deep through domain-specific portals. These portals rely on external knowledge bases, respectively ontologies, mapping to more general concepts allowing for suitable classifications and navigational browsing. Since automatically generated ontologies still not satisfactory advanced information retrieval tasks, most heavily hand-crafted ontologies. This, however, also leads high creation maintaining costs. On other hand, a freely available community maintained, if somewhat general, base is offered by Wikipedia. During last years coverage of Wikipedia has reached large pool including articles from almost all domains. In this paper, we investigate use categories describe content chemical compact form. We compare results ChEBI ontology show that indeed allow useful descriptions even better than ontology.