@techreport{ilprints421,
          number = {1999-65},
           month = {November},
          author = {Sergey Brin},
            note = {Previous number = SIDL-WP-1999-0119},
            type = {Technical Report},
           title = {Extracting Patterns and Relations from the World Wide Web.},
       publisher = {Stanford InfoLab},
            year = {1999},
     institution = {Stanford InfoLab},
         journal = {WebDB Workshop at EDBT'98},
             url = {http://ilpubs.stanford.edu:8090/421/},
        abstract = {The World Wide Web is a vast resource for information. At the same time it is extremely distributed. A particular type of data such as restaurant lists may be scattered across thousands of independent information sources in many different formats. In this paper, we consider the problem of extracting a relation for such a data type from all of these sources automatically. We present a technique which exploits the duality between sets of patterns and relations to grow the target relation starting from a small sample. To test our technique we use it to extract a relation of (author, title) pairs from the World Wide Web.}
}