Enabling Quality Control for Entity Resolution: A Human and Machine Cooperation Framework
Abstract
Even though many machine algorithms have been proposed for entity resolution, it remains very challenging to find a solution with quality guarantees. In this paper, we propose a novel HUman and Machine cOoperation (HUMO) framework for entity resolution (ER), which divides an ER workload between the machine and the human. HUMO enables a mechanism for quality control that can flexibly enforce both precision and recall levels. We introduce the optimization problem of HUMO, minimizing human cost given a quality requirement, and then present three optimization approaches: a conservative baseline one purely based on the monotonicity assumption of precision, a more aggressive one based on sampling and a hybrid one that can take advantage of the strengths of both previous approaches. Finally, we demonstrate by extensive experiments on real and synthetic datasets that HUMO can achieve high-quality results with reasonable return on investment (ROI) in terms of human cost, and it performs considerably better than the state-of-the-art alternatives in quality control.
Cite
@article{arxiv.1710.00204,
title = {Enabling Quality Control for Entity Resolution: A Human and Machine Cooperation Framework},
author = {Zhaoqiang Chen and Qun Chen and Fengfeng Fan and Yanyan Wang and Zhuo Wang and Youcef Nafa and Zhanhuai Li and Hailong Liu and Wei Pan},
journal= {arXiv preprint arXiv:1710.00204},
year = {2018}
}
Comments
12 pages, 11 figures. Camera-ready version of the paper submitted to ICDE 2018, In Proceedings of the 34th IEEE International Conference on Data Engineering (ICDE 2018)