ER-Evaluation 1.0.2

An end-to-end evaluation framework for entity resolution systems.

🔎 ER-Evaluation: An End-to-End Evaluation Framework for Entity Resolution Systems

ER-Evaluation is a Python package for the evaluation of entity resolution (ER) systems. It provides data structure definitions, summary statistics, visualizations, error analysis tools, and statistically principled performance estimators.

Installation

Install the released version from PyPI using:

pip install er-evaluation

Documentation

Please refer to the documentation website olivierbinette.ca/er-evaluation.

Acknowledgements

ER-Evaluation is an extension of the PatentsView/PatentsView-Evaluation project sponsored by the American Institutes for Research and the U.S. Patents and Trademarks Office. We aim to provide a unified source of evaluation tools for entity resolution systems which are maintained as an open source academic project.

Publications

• Binette, Olivier, Sokhna A York, Emma Hickerson, Youngsoo Baek, Sarvo Madhavan, Christina Jones. (2022). Estimating the Performance of Entity Resolution Algorithms: Lessons Learned Through PatentsView.org. arXiv e-prints: arxiv:2210.01230

• Upcoming: "A Statistical Evaluation Framework for Black-Box Entity Resolution Systems With Application to Inventor Name Disambiguation"

Funding

This project was made possible through support from the Natural Sciences and Engineering Research Council of Canada, Fonds de Recherche du Québec - Nature et Technologies, Duke University, the American Institutes for Research, and the U.S. Patents and Trademarks Office.

Citation

Please acknowledge the above publications as well as the ER-Evaluation Python package:

• Binette, Olivier. (2022). ER-Evaluation: An End-to-End Evaluation Framework for Entity Resolution Systems. Available online at https://github.com/OlivierBinette/ER-Evaluation