@incollection{Leonard2011, title = {Applying {{Machine Learning Diversity Metrics}} to {{Data Fusion}} in {{Information Retrieval}}}, booktitle = {Advances in Information Retrieval - 33rd European Conference on {{IR}} Research {{ECIR}} 2011, Dublin, Ireland, April 18-21, 2011. Proceedings.}, author = {Leonard, David and Lillis, David and Toolan, Fergus and Zhang, Lusheng and Collier, Rem W. and Dunnion, John}, editor = {Clough, Paul and Foley, Colum and Gurrin, Cathal and Jones, Gareth J. F. and Kraaij, Wessel and Lee, Hyowon and Mudoch, Vanessa}, year = {2011}, series = {Lecture Notes in Computer Science}, volume = {6611}, pages = {695--698}, publisher = {Springer Berlin Heidelberg}, address = {Dublin, Ireland}, doi = {10.1007/978-3-642-20161-5_73}, abstract = {The Supervised Machine Learning task of classification has parallels with Information Retrieval (IR): in each case, items (documents in the case of IR) are required to be categorised into discrete classes (relevant or non-relevant). Thus a parallel can also be drawn between classifier ensembles, where evidence from multiple classifiers are combined to achieve a superior result, and the IR data fusion task. This paper presents preliminary experimental results on the applicability of classifier ensemble diversity metrics in data fusion. Initial results indicate a relationship between the quality of the fused result set (as measured by MAP) and the diversity of its inputs.}, isbn = {978-3-642-20160-8}, }