PROJECT TITLE :

Signal Processing and Optimization Tools for Conference Review and Session Assignment

ABSTRACT:

Anyone who has served as a technical program committee (TPC) chair for a conference (or program manager for a funding agency) understands that paper (or proposal panel) review assignment is a demanding job that takes a heap of time, and reviewers are rarely happy with the top results. This text presents signal processing tools for two crucial ?mass assignment? tasks: assigning papers (or proposals) to reviewers during a manner that matches reviewing expertise to scientific content while respecting the reviewers? capability constraints and splitting accepted papers (or submitted proposals) to sessions (panels) whereas adhering to session (panel) capability constraints. The fundamental plan is to use feature vectors to represent papers and reviewers. Features will be key words or phrases (e.g., optimization or sensor networks) or different varieties of attributes (e.g., timeliness). This viewpoint permits optimal assignment downside formulations that build sense from a scientific and sensible purpose of view. While optimal solutions are arduous to compute for a giant range of papers and reviewers, high-quality approximate solutions of moderate complexity are developed here using acquainted signal processing and optimization tools. These algorithmic solutions simply outperform days of knowledgeable manual work as demonstrated in experiments with real conference data.