@inproceedings{dab455b0ca324d62a55d7ab4b38d0f33,
title = "Unsupervised Measuring of Entity Resolution Consistency",
abstract = "Entity resolution (ER) is a common data cleaning and data-integration task that aims to determine which records in one or more data sets refer to the same real-world entities. In most cases no training data exists and the ER process involves considerable trial and error, with an often time-consuming manual evaluation required to determine whether the obtained results are good enough. We propose a method that makes use of transitive closure within triples of records to provide an early indication of inconsistency in an ER result in an unsupervised fashion. We test our approach on three real-world data sets with different similarity calculations and blocking approaches and show that our approach can detect problems with ER resultsearly on without a manual evaluation.",
author = "Jeffrey Fisher and Qing Wang",
note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 15th IEEE International Conference on Data Mining Workshop, ICDMW 2015 ; Conference date: 14-11-2015 Through 17-11-2015",
year = "2016",
month = jan,
day = "29",
doi = "10.1109/ICDMW.2015.162",
language = "English",
series = "Proceedings - 15th IEEE International Conference on Data Mining Workshop, ICDMW 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "218--221",
editor = "Xindong Wu and Alexander Tuzhilin and Hui Xiong and Dy, {Jennifer G.} and Charu Aggarwal and Zhi-Hua Zhou and Peng Cui",
booktitle = "Proceedings - 15th IEEE International Conference on Data Mining Workshop, ICDMW 2015",
address = "United States",
}