Clean Answers over Dirty Databases: A Probabilistic Approach Export

@inproceedings{1129890, abstract = {The detection of duplicate tuples, corresponding to the same real-world entity, is an important task in data integration and cleaning. While many techniques exist to identify such tuples, the merging or elimination of duplicates can be a difficult task that relies on ad-hoc and often manual solutions. We propose a complementary approach that permits declarative query answering over duplicated data, where each duplicate is associated with a probability of being in the clean database. We rewrite queries over a database containing duplicates to return each answer with the probability that the answer is in the clean database. Our rewritten queries are sensitive to the semantics of duplication and help a user understand which query answers are most likely to be present in the clean database. The semantics that we adopt is independent of the way the probabilities are produced, but is able to effectively exploit them during query answering. In the absence of external knowledge that associates each database tuple with a probability, we offer a technique, based on tuple summaries, that automates this task. We experimentally study the performance of our rewritten queries. Our studies show that the rewriting does not introduce a significant overhead in query execution time. This work is done in the context of the ConQuer project at the University of Toronto, which focuses on the efficient management of inconsistent and dirty databases.}, address = {Washington, DC, USA}, author = {Andritsos, Periklis and Fuxman, Ariel and Miller, Renee J.}, booktitle = {ICDE '06: Proceedings of the 22nd International Conference on Data Engineering}, citeulike-article-id = {4015350}, citeulike-linkout-0 = {http://dx.doi.org/http://dx.doi.org/10.1109/ICDE.2006.35}, citeulike-linkout-1 = {http://www.cs.toronto.edu/~afuxman/publications/icde06.pdf}, doi = {http://dx.doi.org/10.1109/ICDE.2006.35}, keywords = {entityguides, inconsistent, probabilistic, schema, schema\_matching}, pages = {30}, posted-at = {2009-02-06 11:08:12}, priority = {2}, publisher = {IEEE Computer Society}, title = {Clean Answers over Dirty Databases: A Probabilistic Approach}, url = {http://dx.doi.org/http://dx.doi.org/10.1109/ICDE.2006.35}, year = {2006} }

TY - CONF ID - 1129890 L3 - citeulike-article-id:4015350 N2 - The detection of duplicate tuples, corresponding to the same real-world entity, is an important task in data integration and cleaning. While many techniques exist to identify such tuples, the merging or elimination of duplicates can be a difficult task that relies on ad-hoc and often manual solutions. We propose a complementary approach that permits declarative query answering over duplicated data, where each duplicate is associated with a probability of being in the clean database. We rewrite queries over a database containing duplicates to return each answer with the probability that the answer is in the clean database. Our rewritten queries are sensitive to the semantics of duplication and help a user understand which query answers are most likely to be present in the clean database. The semantics that we adopt is independent of the way the probabilities are produced, but is able to effectively exploit them during query answering. In the absence of external knowledge that associates each database tuple with a probability, we offer a technique, based on tuple summaries, that automates this task. We experimentally study the performance of our rewritten queries. Our studies show that the rewriting does not introduce a significant overhead in query execution time. This work is done in the context of the ConQuer project at the University of Toronto, which focuses on the efficient management of inconsistent and dirty databases. AD - Washington, DC, USA EP - 30 TI - Clean Answers over Dirty Databases: A Probabilistic Approach PB - IEEE Computer Society T2 - ICDE '06: Proceedings of the 22nd International Conference on Data Engineering KW - entityguides KW - inconsistent KW - probabilistic KW - schema KW - schema_matching AU - Andritsos, Periklis AU - Fuxman, Ariel AU - Miller, Renee PY - 2006/// UR - http://dx.doi.org/http://dx.doi.org/10.1109/ICDE.2006.35 ER -