Tagpedia: a Semantic Reference to Describe and Search for Web Resources.
SWKM, volume 356 of CEUR Workshop Proceedings, CEUR-WS.org, (2008)Abstract
Nowadays the Web represents a growing collection of anenormous amount of contents where the need for betterways to find and organize the available data is becominga fundamental issue, in order to deal with information over-load. Keyword based Web searches are actually the pre-ferred mean to seek for contents related to a specific topic.Search engines and collaborative tagging systems make pos-sible the search for information thanks to the association ofdescriptive keywords to Web resources. All of them showproblems of inconsistency and consequent reduction of re-call and precision of searches, due to polysemy, synonymyand in general all the different lexical forms that can be usedto refer to a particular meaning. A possible way to face orat least reduce these problems is represented by the intro-duction of semantics to characterize the contents of Web re-sources: each resource is described by one or more conceptsinstead of simple and often ambiguous keywords. To supportthese task the availability of a global semantic resource ofreference is fundamental. On the basis of our past experiencewith the semantic tagging of Web resources and the SemKeyProject, we are developing Tagpedia, a general-domain ”en-cyclopedia” of tags, semantically structured for generatingsemantic descriptions of contents over the Web, created bymining Wikipedia. In this paper, starting from an analy-sis of the weak points of non-semantic keyword based Websearches, we introduce our idea of semantic characterizationof Web resources describing the structure and organizationof Tagpedia. We introduce our first realization of Tagpedia,suggesting all the possible improvements that can be carriedout in order to exploit its full potential
