One of the central issues in learning to rank for information retrieval is to develop algorithms that construct ranking models by directly optimizing evaluation measures used in i...
Past research has identified many different types of relevance in information retrieval (IR). So far, however, most evaluation of IR systems has been through batch experiments cond...
The empirical investigation of the effectiveness of information retrieval (IR) systems requires a test collection, a set of query topics, and a set of relevance judgments made by ...
ImageCLEFphoto 2008 is an ad-hoc photo retrieval task and part of the ImageCLEF evaluation campaign. This task provides both the resources and the framework necessary to perform c...
Thomas Arni, Paul Clough, Mark Sanderson, Michael ...
We introduce and validate bootstrap techniques to compute confidence intervals that quantify the effect of test-collection variability on average precision (AP) and mean average...