diff --git a/CHANGELOG.md b/CHANGELOG.md index cfb4bb0..3be309e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,9 @@ # Changelog +## 1.0.1 (November 14, 2022) + +- FIX: Replace sklearn dependency with scikit-learn. Add scipy dependency. + ## 1.0.0 (November 4, 2022) - Added assignee benchmark datasets diff --git a/paper/main.tex b/paper/main.tex index a021cfd..845db97 100644 --- a/paper/main.tex +++ b/paper/main.tex @@ -1,6 +1,6 @@ \documentclass[fontsize=11pt]{article} -\renewcommand{\baselinestretch}{1.2} +\renewcommand{\baselinestretch}{2} \usepackage[english]{babel} @@ -82,7 +82,7 @@ \maketitle \begin{abstract} -This paper introduces a novel evaluation methodology for entity resolution algorithms. It is motivated by PatentsView.org, a {U.S. Patents and Trademarks Office patent data exploration tool} that disambiguates patent inventors using an entity resolution algorithm. We provide a data collection methodology and tailored performance estimators that account for sampling biases. Our approach is simple, practical and principled -- key characteristics that allow us to paint the first representative picture of PatentsView's disambiguation performance. This approach is used to inform PatentsView's users of the reliability of the data and to allow the comparison of competing disambiguation algorithms. +This paper introduces a novel evaluation methodology for entity resolution algorithms. It is motivated by PatentsView.org, a U.S. Patents and Trademarks Office patent data exploration tool that disambiguates patent inventors using an entity resolution algorithm. We provide a data collection methodology and tailored performance estimators that account for sampling biases. Our approach is simple, practical and principled -- key characteristics that allow us to paint the first representative picture of PatentsView's disambiguation performance. This approach is used to inform PatentsView's users of the reliability of the data and to allow the comparison of competing disambiguation algorithms. \end{abstract} \section{Introduction} diff --git a/setup.py b/setup.py index f813924..6fd2a76 100644 --- a/setup.py +++ b/setup.py @@ -4,7 +4,7 @@ if __name__ == "__main__": setup( name="pv_evaluation", - version="1.0.0", + version="1.0.1", license_files = ('LICENSE.txt',), author="Olivier Binette, Sarvo Madhavan", author_email="olivier.binette@gmail.com", @@ -20,7 +20,8 @@ "python-snappy", "numpy", "plotly", - "sklearn", + "scikit-learn", + "scipy", "quarto", "jinja2", "kaleido",