Efficient Computation of Diverse Query Results

@inproceedings{citeulike:3001647, abstract = {We study the problem of efficiently computing diverse query results in online shopping applications, where users specify queries through a form interface that allows a mix of structured and content-based selection conditions. Intuitively, the goal of diverse query answering is to return a representative set of top-k answers from all the tuples that satisfy the user selection condition. For example, if a user is searching for Honda cars and we can only display five results, we wish to return cars from five different Honda models, as opposed to returning cars from only one or two Honda models. A key contribution of this paper is to formally define the notion of diversity, and to show that existing score based techniques commonly used in web applications are not sufficient to guarantee diversity. Another contribution of this paper is to develop novel and efficient query processing techniques that guarantee diversity. Our experimental results using Yahoo! Autos data show that our proposed techniques are scalable and efficient.}, author = {Vee, E. and Srivastava, U. and Shanmugasundaram, J. and Bhat, P. and Yahia, S. A. }, booktitle = {Data Engineering, 2008. ICDE 2008. IEEE 24th International Conference on}, citeulike-article-id = {3001647}, doi = {http://dx.doi.org/10.1109/ICDE.2008.4497431}, journal = {Data Engineering, 2008. ICDE 2008. IEEE 24th International Conference on}, keywords = {search, xml}, pages = {228--236}, posted-at = {2008-07-15 10:44:39}, priority = {0}, title = {Efficient Computation of Diverse Query Results}, url = {http://dx.doi.org/10.1109/ICDE.2008.4497431}, year = {2008} }

TY - CONF ID - citeulike:3001647 L3 - citeulike-article-id:3001647 TI - Efficient Computation of Diverse Query Results T2 - Data Engineering, 2008. ICDE 2008. IEEE 24th International Conference on JF - Data Engineering, 2008. ICDE 2008. IEEE 24th International Conference on SP - 228 EP - 236 N2 - We study the problem of efficiently computing diverse query results in online shopping applications, where users specify queries through a form interface that allows a mix of structured and content-based selection conditions. Intuitively, the goal of diverse query answering is to return a representative set of top-k answers from all the tuples that satisfy the user selection condition. For example, if a user is searching for Honda cars and we can only display five results, we wish to return cars from five different Honda models, as opposed to returning cars from only one or two Honda models. A key contribution of this paper is to formally define the notion of diversity, and to show that existing score based techniques commonly used in web applications are not sufficient to guarantee diversity. Another contribution of this paper is to develop novel and efficient query processing techniques that guarantee diversity. Our experimental results using Yahoo! Autos data show that our proposed techniques are scalable and efficient. KW - search KW - xml AU - Vee, E AU - Srivastava, U AU - Shanmugasundaram, J AU - Bhat, P AU - Yahia, SA PY - 2008/// UR - http://dx.doi.org/10.1109/ICDE.2008.4497431 ER -