%0 Conference Paper %1 Yu2006Schema %A Yu, Cong %A Jagadish, H. V. %B Very Large Data Bases %C Seoul, Korea %D 2006 %I VLDB Endowment %K review schema summarisation phd schema_summary schemdesc %P 319--330 %R http://dx.doi.org/10.1016/S0169-023X(96)00007-9 %T Schema Cummarization %U http://portal.acm.org/citation.cfm?id=1164156 http://dx.doi.org/10.1016/S0169-023X(96)00007-9 %X Real database systems can often be very complex. A person wishing to access data from an unfamiliar database has the daunting task of understanding its schema before being able to pose a correct query against it. A schema summary can be of great help, providing a succinct overview of the entire schema, and making it possible to explore in depth only the relevant schema components.In this paper we formally define a schema summary and two desirable properties (in addition to minimizing size) of a summary: presenting important schema elements and achieving broad information coverage. We develop algorithms that allow us to automatically generate schema summaries based on these two goals. We further develop an objective metric for assessing the quality of a schema summary using query information. Experimental evaluation using this metric demonstrates that the summaries produced by our algorithms can significantly reduce the amount of user effort required to formulate a query through schema exploration. %Z From Duplicate 1 ( Schema summarization - Yu, Cong; Jagadish, H. V. )

@inproceedings{Yu2006Schema, abstract = {Real database systems can often be very complex. A person wishing to access data from an unfamiliar database has the daunting task of understanding its schema before being able to pose a correct query against it. A schema summary can be of great help, providing a succinct overview of the entire schema, and making it possible to explore in depth only the relevant schema components.In this paper we formally define a schema summary and two desirable properties (in addition to minimizing size) of a summary: presenting important schema elements and achieving broad information coverage. We develop algorithms that allow us to automatically generate schema summaries based on these two goals. We further develop an objective metric for assessing the quality of a schema summary using query information. Experimental evaluation using this metric demonstrates that the summaries produced by our algorithms can significantly reduce the amount of user effort required to formulate a query through schema exploration.}, added-at = {2013-12-17T09:48:27.000+0100}, address = {Seoul, Korea}, annote = { From Duplicate 1 ( Schema summarization - Yu, Cong; Jagadish, H. V. ) }, author = {Yu, Cong and Jagadish, H. V.}, biburl = {https://www.bibsonomy.org/bibtex/2354ba5260e0bb3a118ed58c3a3596f9e/jullybobble}, booktitle = {Very Large Data Bases}, doi = {http://dx.doi.org/10.1016/S0169-023X(96)00007-9}, file = {:Users/julien.gaugaz/Dropbox/Papers/Mendeley Desktop/2008/Wang et al. - 2008 - Multi-document summarization via sentence-level semantic analysis and symmetric matrix factorization.pdf:pdf}, interhash = {9e98224b7fa759d0dc6853d7efd1b9c4}, intrahash = {354ba5260e0bb3a118ed58c3a3596f9e}, keywords = {review schema summarisation phd schema_summary schemdesc}, mendeley-tags = {review,schema,summarisation}, pages = {319--330}, publisher = {VLDB Endowment}, timestamp = {2014-07-27T15:43:19.000+0200}, title = {{Schema Cummarization}}, url = {http://portal.acm.org/citation.cfm?id=1164156 http://dx.doi.org/10.1016/S0169-023X(96)00007-9}, year = 2006 }