Wikipedia is a goldmine of information; not just for its many readers, but
so for the growing community of researchers who recognize it as a resource of
ceptional scale and utility. It represents a vast investment of manual effort
d judgment: a huge, constantly evolving tapestry of concepts and relations
at is being applied to a host of tasks.
This article provides a comprehensive description of this work. It focuses on
search that extracts and makes use of the concepts, relations, facts and
scriptions found in Wikipedia, and organizes the work into four broad
tegories: applying Wikipedia to natural language processing; using it to
cilitate information retrieval and information extraction; and as a resource
r ontology building. The article addresses how Wikipedia is being used as is,
w it is being improved and adapted, and how it is being combined with other
ructures to create entirely new resources. We identify the research groups
d individuals involved, and how their work has developed in the last few
ars. We provide a comprehensive list of the open-source software they have
oduced. We also discuss the implications of this work for the long-awaited
mantic web.

This paper describes a new technique for obtaining measures of semantic relatedness. Like other recent approaches, it uses Wikipedia to provide structured world knowledge about the terms of interest. Out approach is unique in that it does so using the hyperlink structure of Wikipedia rather than its category hierarchy or textual content. Evaluation with manually defined measures of semantic relatedness reveals this to be an effective compromise between the ease of computation of the former approach and the accuracy of the latter.