Abstract: Rating information retrieval algorithms. A query is received and submitted to a search engine for execution on an index file. A list of index documents and a plurality of attributes are received from the search engine in response to the submitted query. A portion of the received list of index documents and the received plurality of attributes are stored in a subindex file. The received query is executed on the subindex file to obtain a list of subindex documents. The obtained list of subindex documents is ranked by a particular ranking algorithm using the attributes associated therewith. The list of ranked subindex documents is compared with a list of subjectively ranked documents to generate a score for the particular ranking algorithm. The generated score represents a degree of correlation between the list of ranked subindex documents and the list of subjectively ranked documents.

Abstract: A system and a method for locating and presenting electronic documents most-likely of interest to the user. A plurality of search terms to be located in a set of electronic document is received. One of the search terms is selected as the anchor term, and occurrences of the anchor term are located within the documents. For each located occurrence of the anchor term, a set of search term occurrences is selected. These sets include an occurrence of each search term, and the occurrences are selected by choosing the search term occurrences that are closest to a desired placement for the search terms. With each set of search terms, the method associates a value indicating the extent to which the selected occurrences vary from the desired placement. The electronic documents are ranked and presented to the user in accordance with this value. The invention further includes systems and methods for locating and presenting Web pages and for searching the Internet.

Abstract: Improving ranking algorithms for information retrieval. The ranking algorithms operate on search results obtained from a search engine. Input information including information describing a first ranking algorithm, a first score associated with the first ranking algorithm, a second ranking algorithm, a second score associated with the second ranking algorithm, and causal information relating a difference between the first ranking algorithm and the second ranking algorithm with a difference between the first score and the second score is received. An optimizing algorithm is applied to the received input information to identify an optimal ranking algorithm having an optimal score. The optimal ranking algorithm is defined by a plurality of parameters and a plurality of weights associated with the plurality of parameters.