@inproceedings{f035c895a6314f95b3eb3b69626b2422,
title = "Probabilistic Data Integration",
abstract = "In data integration efforts such as in portal development, much development time is devoted to entity resolution. Often advanced similarity measurement techniques are used to remove semantic duplicates or solve other semantic conflicts. It proofs impossible, however, to automatically get rid of all semantic problems. An often-used rule of thumb states that about 90% of the development effort is devoted to semi-automatically resolving the remaining 10% hard cases. In an attempt to significantly decrease human effort at data integration time, we have proposed an approach that strives for a 'good enough' initial integration which stores any remaining semantic uncertainty and conflicts in a probabilistic XML database. The remaining cases are to be resolved during use with user feedback. We conducted extensive experiments on the effects and sensitivity of rule denition, threshold tuning, and user feedback on the integration quality. We claim that our approach indeed reduces development effort - and not merely shifts the effort - by showing that setting rough safe thresholds and defining only a few rules suffices to produce a 'good enough' integration that can be meaningfully used, and that user feedback is effective in gradually improving the integration quality.",
keywords = "probabilistic databases, EWI-15237, Uncertainty management, METIS-265199, data quality, IR-65438, Data Integration, entity resolution",
author = "{van Keulen}, Maurice",
note = "http://eprints.ewi.utwente.nl/15237 ; Uncertainty Management in Information Systems : Dagstuhl Seminar 08421 ; Conference date: 12-10-2008 Through 17-10-2008",
year = "2009",
month = mar,
language = "English",
series = "Dagstuhl Seminar Proceedings",
publisher = "Dagstuhl",
number = "08421",
pages = "8--8",
editor = "Christoph Koch and Birgitta K{\"o}nig-Ries and Volker Markl and {van Keulen}, Maurice",
booktitle = "08421 Abstracts Collection - Uncertainty Management in Information Systems",
address = "Germany",
}