K.L. Liu, W. Meng, C. Yu. (2001). Discovery of similarity computations of search engines, Proceedings of the ninth international conference on Information and knowledge management. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Discovery of Similarity Computations of Search Engines - Liu, Meng, Yu (2000) (1 citation) Self-citation (Liu Meng Yu) (Correct)
....= 1, 2) If with respect to Q t 1 ;t 2 , d1 has a higher rank, we replace the ratio in U by R , otherwise the ratio in L is replaced by R. This process is repeated until the difference between U and R is less than some pre determined positive number. The details of the algorithm is given in [12]. Using the above steps, we can form as many equations involving the embedded constants as we want. When enough equations are constructed, it is possible to solve for the sets of constants K; A; B and C. We have developed a systematic procedure which facilitates the solution of the unknown ....
....Using the above steps, we can form as many equations involving the embedded constants as we want. When enough equations are constructed, it is possible to solve for the sets of constants K; A; B and C. We have developed a systematic procedure which facilitates the solution of the unknown constants [12]. 4. DERIVATION OF TERM WEIGHT FORMULAS The possible formulas for determining the term weight components are theoretically infinite. However, from the retrieval results of probe queries, we can often derive approximately (sometimes precisely) for a term weight component its mathematical formula ....
[Article contains additional citation context not shown here]
K. Liu, W. Meng, C. Yu, and N. Rishe. Discovery of similarity computations of search engines. Technical report, Depaul University, 2000. (http://www.depaul.edu/kliu/disc sim.ps)
Building Efficient and Effective Metasearch Engines - Meng, Yu, Liu (2002) (11 citations) Self-citation (Liu Meng Yu) (Correct)
....Furthermore, this approach requires the knowledge of the similarity function and the term weighting formula used in a component system. The information is likely to be proprietary and may not be easily available. A work on discovering such information based on sampling queries is reported in [42]. Computing the Tightest Local Threshold For a given query q, suppose the metasearch engine sets a threshold T and uses a global similarity function G such that any document d that satisfies G(q; d) T is to be retrieved (i.e. the document is considered to be potentially useful) The problem ....
....rank of the document in the merged list. To know whether independent ranking algorithms are used in different search engines, we need to find out what similarity functions and term weighting formulas are used in different component systems. A technique on discovering such knowledge is reported in [42]. 7.2 Global Similarity Estimation Under certain conditions, it is possible to compute or estimate the global similarities of returned documents. The following methods have been reported. 7.2.1 Document Fetching That a document is returned by a search engine typically means that the URL of the ....
[Article contains additional citation context not shown here]
K. Liu, W. Meng, and C. Yu. Discovery of Similarity Computations of Search Engines. Nineth ACM International Conference on Information and Knowledge Management (CIKM'00), Washington, D.C., November 2000.
Modeling Search Engine Effectiveness for Federated Search - Si, Callan (Correct)
No context found.
K.L. Liu, W. Meng, C. Yu. (2001). Discovery of similarity computations of search engines, Proceedings of the ninth international conference on Information and knowledge management.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC