@techreport{ilprints526,
          number = {2001-8},
          author = {Taher Haveliwala and Aristides Gionis and Dan Klein and Piotr Indyk},
           title = {Similarity Search on the Web: Evaluation and Scalability Considerations},
            type = {Technical Report},
       publisher = {Stanford},
     institution = {Stanford InfoLab},
         journal = {Technical Report},
            year = {2001},
        keywords = {web search, related pages, similarity search, clustering},
             url = {http://ilpubs.stanford.edu:8090/526/},
        abstract = {Allowing users to find pages on the web similar to a particular query page is a crucial component of modern search engines.  A variety of techniques and approaches exist to support "Related Pages" queries.  In this paper we discuss shortcomings of previous approaches and present a unifying approach that puts special emphasis on the use of text, both within anchors and surrounding anchors.  In the central contribution of our paper, we present a novel technique for automating the evaluation process, allowing us to tune our parameters to maximize the quality of the results.  Finally, we show how to scale our approach to millions of web pages, using the established Locality-Sensitive-Hashing technique.}
}