@inproceedings{5ba23c2d612c402ebf9703dc3c3f3223,
title = "Automatically building probabilistic databases from the web",
abstract = "A relevant number of web sites publish structured data about recognizable concepts (such as stock quotes, movies, restau- rants, etc.). There is a great chance to create applications that rely on a huge amount of data taken from the Web. We present an automatic and domain independent system that performs all the steps required to benefit from these data: it discovers data intensive web sites containing information about an entity of interest, extracts and integrate the published data, and finally performs a probabilistic analysis to characterize the impreciseness of the data and the accuracy of the sources. The results of the processing can be used to populate a probabilistic database.",
keywords = "data integration, probabilistic data, web data extraction",
author = "Lorenzo Blanco and Mirko Bronzi and Valter Crescenzi and Paolo Merialdo and Paolo Papotti",
year = "2011",
doi = "10.1145/1963192.1963285",
language = "English (US)",
isbn = "9781450305181",
series = "Proceedings of the 20th International Conference Companion on World Wide Web, WWW 2011",
pages = "185--188",
booktitle = "Proceedings of the 20th International Conference Companion on World Wide Web, WWW 2011",
note = "20th International Conference Companion on World Wide Web, WWW 2011 ; Conference date: 28-03-2011 Through 01-04-2011",
}