caa a22 4500 463251512 CHVBK 20180405153341.0 cr unu---uuuuu 170326e20070601xx s 000 0 eng 10.1007/s10791-006-9019-z doi (NATIONALLICENCE)springer-10.1007/s10791-006-9019-z Linear feature-based models for information retrieval [Elektronische Daten] [Donald Metzler, W. Bruce Croft] There have been a number of linear, feature-based models proposed by the information retrieval community recently. Although each model is presented differently, they all share a common underlying framework. In this paper, we explore and discuss the theoretical issues of this framework, including a novel look at the parameter space. We then detail supervised training algorithms that directly maximize the evaluation metric under consideration, such as mean average precision. We present results that show training models in this way can lead to significantly better test set performance compared to other training methods that do not directly maximize the metric. Finally, we show that linear feature-based models can consistently and significantly outperform current state of the art retrieval models with the correct choice of features. Springer Science+Business Media, LLC, 2006 Retrieval models nationallicence Linear models nationallicence Features nationallicence Direct maximization nationallicence Metzler Donald University of Massachusetts, Amherst, MA, USA aut Bruce Croft W. University of Massachusetts, Amherst, MA, USA aut Information Retrieval Kluwer Academic Publishers 10/3(2007-06-01), 257-274 1386-4564 10:3<257 2007 10 10791 https://doi.org/10.1007/s10791-006-9019-z text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s10791-006-9019-z text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Metzler Donald University of Massachusetts, Amherst, MA, USA aut NATIONALLICENCE 700 1- Bruce Croft W. University of Massachusetts, Amherst, MA, USA aut NATIONALLICENCE 773 0- Information Retrieval Kluwer Academic Publishers 10/3(2007-06-01), 257-274 1386-4564 10:3<257 2007 10 10791 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer