@techreport{TD:101508,
	att_abstract={{Recent research shows that copying is prevalent for Deep-Web data and considering copying can significantly improve truth finding from conflicting values. However, existing copy detection techniques do not scale for large sizes and numbers of data sources, so truth finding can be slowed down by one to two orders of magnitude compared with the corresponding techniques that do not consider copying. In this paper, we study how to improve scalability of copy detection on structured data.

Our algorithm builds an inverted index for each shared value and processes the index entries in decreasing orders of how much the shared value can contribute to the conclusion of copying. We show how we use the index to prune the data items we consider for each pair of sources, and to incrementally refine our results
in iterative copy detection. We also apply a sampling strategy with which we are able to further reduce copy-detection time while still obtaining very similar results as on the whole data set. Experiments on various real data sets show that our algorithm can reduce the time for copy detection by two to three orders of magnitude; in other words, truth finding can benefit from copy detection with very little overhead.}},
	att_authors={ds8961, kl5165},
	att_categories={C_BB.1, C_IIS.5, C_NSS.2},
	att_copyright={{IEEE}},
	att_copyright_notice={{This version of the work is reprinted here with permission of IEEE for your personal use. Not for redistribution. The definitive version was published in 2014. {{, 2015-04-13}}
}},
	att_donotupload={},
	att_private={false},
	att_projects={},
	att_tags={},
	att_techdoc={true},
	att_techdoc_key={TD:101508},
	att_url={http://web1.research.att.com:81/techdocs_downloads/TD:101508_DS1_2014-10-21T21:50:42.786Z.pdf},
	author={Divesh Srivastava and Kenneth Lyons and Xian Li and Xin Luna Dong and Weiyi Meng},
	institution={{IEEE International Conference on Data Engineering}},
	month={April},
	title={{Scaling up Copy Detection}},
	year=2015,
}