@inproceedings{34c315fec46a469b89ea27c265c8a839,
title = "Join query processing in data quality management",
abstract = "Data quality management is the essential problem for information systems. As a basic operation of Data quality management, joins on large-scale data play an important role in document clustering. MapReduce is a programming model which is usually applied to process large-scale data. Many tasks can be implemented under the framework, such as data processing of search engines and machine learning. However, there is no efficient support for join operation in current implementations of MapReduce. In this paper, we present a strategies to build the extend bloom filter for the large dataset using MapReduce. We use the extend bloom filter to improve the performance of two-way and multi-way joins.",
keywords = "Bloom filter, Data quality management, Join, MapReduce",
author = "Mingliang Yue and Hong Gao and Shengfei Shi and Hongzhi Wang",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; International Workshop on Database Systems for Advanced Applications, DASFAA 2016 ; Conference date: 16-04-2016 Through 19-04-2016",
year = "2016",
doi = "10.1007/978-3-319-32055-7\_27",
language = "英语",
isbn = "9783319320540",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "329--342",
editor = "Jinho Kim and Hong Gao and Yasushi Sakurai",
booktitle = "Database Systems for Advanced Applications - DASFAA 2016 International Workshops",
address = "德国",
}