@inproceedings{ef72536976924e5dbf3c9a26a68c3cf8,
title = "BayesWipe: A multimodal system for data cleaning and consistent query answering on structured bigdata",
abstract = "Recent efforts in data cleaning of structured data have focused exclusively on problems like data deduplication, record matching, and data standardization; none of these focus on fixing incorrect attribute values in tuples. Correcting values in tuples is typically performed by a minimum cost repair of tuples that violate static constraints like CFDs (which have to be provided by domain experts, or learned from a clean sample of the database). In this paper, we provide a method for correcting individual attribute values in a structured database using a Bayesian generative model and a statistical error model learned from the noisy database directly. We thus avoid the necessity for a domain expert or clean master data. We also show how to efficiently perform consistent query answering using this model over a dirty database, in case write permissions to the database are unavailable. We evaluate our methods over both synthetic and real data.",
keywords = "Data cleaning, Databases, Query rewriting, Uncertainty, Web databases",
author = "Sushovan De and Yuheng Hu and Yi Chen and Subbarao Kambhampati",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2nd IEEE International Conference on Big Data, IEEE Big Data 2014 ; Conference date: 27-10-2014 Through 30-10-2014",
year = "2014",
doi = "10.1109/BigData.2014.7004207",
language = "English (US)",
series = "Proceedings - 2014 IEEE International Conference on Big Data, IEEE Big Data 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "15--24",
editor = "Jimmy Lin and Jian Pei and Hu, {Xiaohua Tony} and Wo Chang and Raghunath Nambiar and Charu Aggarwal and Nick Cercone and Vasant Honavar and Jun Huan and Bamshad Mobasher and Saumyadipta Pyne",
booktitle = "Proceedings - 2014 IEEE International Conference on Big Data, IEEE Big Data 2014",
address = "United States",
}