@techreport{TD:101387,
	att_abstract={{Record linkage clusters records such that each cluster corresponds to a single distinct real-world entity. It is a crucial step in data cleaning and data integration. In the big data era, the volume of data is often huge and the velocity of data updates is often high, quickly making previous linkage results obsolete. This paper presents an end-to-end framework that can incrementally and efficiently update linkage results when data updates arrive. Our algorithms not only allow merging records in the updates with existing clusters, but also allow leveraging new evidence from the updates to fix previous linkage errors. Experimental results on three real and synthetic data sets show that our algorithms can significantly reduce linkage time without sacrificing linkage quality.}},
	att_authors={ds8961},
	att_categories={C_BB.1, C_NSS.2, C_IIS.5},
	att_copyright={{VLDB Foundation}},
	att_copyright_notice={{The definitive version was published in Very Large Databases, 2014. {{, 2014-08-31}}
}},
	att_donotupload={},
	att_private={false},
	att_projects={},
	att_tags={},
	att_techdoc={true},
	att_techdoc_key={TD:101387},
	att_url={http://web1.research.att.com:81/techdocs_downloads/TD:101387_DS1_2014-09-14T02:56:30.999Z.pdf},
	author={Divesh Srivastava and Anja Gruenheid and Xin Luna Dong},
	institution={{Proceedings of the VLDB Endowment}},
	month={August},
	title={{Incremental Record Linkage}},
	year=2014,
}