@article{SawadeBickelvonOertzenetal.2013, author = {Sawade, Christoph and Bickel, Steffen and von Oertzen, Timo and Scheffer, Tobias and Landwehr, Niels}, title = {Active evaluation of ranking functions based on graded relevance}, series = {Machine learning}, volume = {92}, journal = {Machine learning}, number = {1}, publisher = {Springer}, address = {Dordrecht}, issn = {0885-6125}, doi = {10.1007/s10994-013-5372-5}, pages = {41 -- 64}, year = {2013}, abstract = {Evaluating the quality of ranking functions is a core task in web search and other information retrieval domains. Because query distributions and item relevance change over time, ranking models often cannot be evaluated accurately on held-out training data. Instead, considerable effort is spent on manually labeling the relevance of query results for test queries in order to track ranking performance. We address the problem of estimating ranking performance as accurately as possible on a fixed labeling budget. Estimates are based on a set of most informative test queries selected by an active sampling distribution. Query labeling costs depend on the number of result items as well as item-specific attributes such as document length. We derive cost-optimal sampling distributions for the commonly used performance measures Discounted Cumulative Gain and Expected Reciprocal Rank. Experiments on web search engine data illustrate significant reductions in labeling costs.}, language = {en} }