@inproceedings{962dcb2413a34394b598054565c0dc74,
title = "Probabilistic reconciliation of records from inaccurate web sources (extended abstract)",
abstract = "Web data are inherently imprecise and uncertain. This paper addresses the issue of characterizing the uncertainty of data extracted from a number of inaccurate sources. We develop a probabilistic model to compute a probability distribution for the extracted values, and the accuracy of the sources. Our model considers the presence of sources that copy their contents from other sources, and manages the misleading consensus produced by copiers. We extend the models previously proposed in the literature by working on several attributes at a time to better leverage all the available evidence of copying.",
author = "Lorenzo Blanco and Valter Crescenzi and Paolo Merialdo and Paolo Papotti",
year = "2010",
month = jan,
day = "1",
language = "English (US)",
isbn = "9788874883691",
series = "SEBD 2010 - Proceedings of the 18th Italian Symposium on Advanced Database Systems",
publisher = "Esculapio Editore",
pages = "390--397",
booktitle = "SEBD 2010 - Proceedings of the 18th Italian Symposium on Advanced Database Systems",
note = "18th Italian Symposium on Advanced Database Systems, SEBD 2010 ; Conference date: 20-06-2010 Through 23-06-2010",
}