%0 Conference Paper %1 Madhavan2007 %A Madhavan, Jayant %A Jeffery, Shawn R. %A Cohen, Shirley %A Dong, Xin (. %A Ko, David %A Yu, Cong %A Halevy, Alon %A Inc, Google %B In Proc. of CIDR-07 %D 2007 %K integration payg %T Web-scale Data Integration: You Can Only Afford to Pay As You Go %U http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.9358 %X The World Wide Web is witnessing an increase in the amount of structured content � vast heterogeneous collections of structured data are on the rise due to the Deep Web, annotation schemes like Flickr, and sites like Google Base. While this phenomenon is creating an opportunity for structured data management, dealing with heterogeneity on the web-scale presents many new challenges. In this paper, we highlight these challenges in two scenarios � the Deep Web and Google Base. We contend that traditional data integration techniques are no longer valid in the face of such heterogeneity and scale. We propose a new data integration architecture, PAYGO, which is inspired by the concept of dataspaces and emphasizes pay-as-you-go data management as means for achieving web-scale data integration. 1.

@inproceedings{Madhavan2007, abstract = {The World Wide Web is witnessing an increase in the amount of structured content � vast heterogeneous collections of structured data are on the rise due to the Deep Web, annotation schemes like Flickr, and sites like Google Base. While this phenomenon is creating an opportunity for structured data management, dealing with heterogeneity on the web-scale presents many new challenges. In this paper, we highlight these challenges in two scenarios � the Deep Web and Google Base. We contend that traditional data integration techniques are no longer valid in the face of such heterogeneity and scale. We propose a new data integration architecture, PAYGO, which is inspired by the concept of dataspaces and emphasizes pay-as-you-go data management as means for achieving web-scale data integration. 1.}, added-at = {2009-06-12T18:16:40.000+0200}, author = {Madhavan, Jayant and Jeffery, Shawn R. and Cohen, Shirley and Dong, Xin (. and Ko, David and Yu, Cong and Halevy, Alon and Inc, Google}, biburl = {https://www.bibsonomy.org/bibtex/2ec6b3cf2f2d3ebc9ca39bf25122367c9/jmora}, booktitle = {In Proc. of CIDR-07}, citeulike-article-id = {3392146}, file = {:Madhavan2007.pdf:PDF}, interhash = {8c25b47e72fb15164cd0d0ebc859fef5}, intrahash = {ec6b3cf2f2d3ebc9ca39bf25122367c9}, keywords = {integration payg}, owner = {jmora}, posted-at = {2008-10-10 03:35:59}, priority = {3}, review = {Este es interesante, entre otras cosas, porque hace un peque�o repaso de las tareas involucradas en un proceso de integraci�n de informaci�n. Yo encantado de trabajar en el pay as you go, pero esto es para V�ctor m�s que para m�. Hace clustering de esquemas, los integra con mappings autom�ticos con poca certeza o manuales con mayor certeza y reutiliza los mappings para hacer bootstrap. Maneja much�simos esquemas y los mappings son dos a dos, porque si no es una locura, as� que si para llegar de un esquema a otro tiene que pasar por otros dos por el camino descrito por los mappings lo hace. Utiliza informaci�n acerca de los resultados, especialmente feedback del usuario (que en google tienen muchos) para mejorar los algoritmos, para ir quitando la incertidumbre, etc.}, timestamp = {2009-06-12T18:28:54.000+0200}, title = {Web-scale Data Integration: You Can Only Afford to Pay As You Go}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.9358}, year = 2007 }