Automatic Ranking of Information Retrieval Systems

Abstract

Typical information retrieval system evaluation requires expensive manually-collected relevance judgments of documents, which are used to rank retrieval systems. Due to the high cost associated with collecting relevance judgments and the ever-growing scale of data to be searched in practice, ranking of retrieval systems using manual judgments is becoming less feasible. Methods to automatically rank systems in absence of judgments have been proposed to tackle this challenge. However, current techniques are still far from reaching the ranking achieved using manual judgments. I propose to advance research on automatic system ranking using supervised and unsupervised techniques.