The relevance-based measures of recall and precision are important for assessing the performance of information retrieval (IR) systems and algorithms. However, it is less clear how important these measures are for assessing the value of IR systems for users. This talk describes a series of experiments in the TREC setting and the medical domain that measure user performance with IR systems and assess, among other factors, the important of recall and precision in that context.
A biography can be found here.
This talk is part of the CLIP Colloquium Series, organized by Jimmy Lin (jimmylin -at- umd .dot. edu). For the complete schedule, please visit http://www.umiacs.umd.edu/research/CLIP/colloq/.