A Framework for Optimizing Paper Matching

摘要

At the heart of many scientific conferences is the problem of matching submitted papers to suit able reviewers. Arriving at a good assignment is a major and important challenge for any confer ence organizer. In this paper we propose a frame work to optimize paper-to-reviewer assignments. Our framework uses suitability scores to measure pairwise affinity between papers and reviewers. We show how learning can be used to infer suit ability scores from a small set of provided scores, thereby reducing the burden on reviewers and or ganizers. We frame the assignment problem as an integer program and propose several variations for the paper-to-reviewer matching domain. We also explore how learning and matching interact. Experiments on two conference data sets exam ine the performance of several learning methods as well as the effectiveness of the matching for mulations.