Parameter sensitivity in the probabilistic model for ad-hoc retrieval

The term frequency normalisation parameter sensitivity is an important issue in the probabilistic model for Information Retrieval. A high parameter sensitivity indicates that a slight change of the parameter value may considerably affect the retrieval performance. Therefore, a weighting model with a high parameter sensitivity is not robust enough to provide a consistent retrieval performance across different collections and queries. In this paper, we suggest that the parameter sensitivity is due to the fact that the query term weights are not adequate enough to allow informative query terms to differ from non-informative ones. We show that query term reweighing, which is part of the relevance feedback process, can be successfully used to reduce the parameter sensitivity. Experiments on five Text REtrieval Conference (TREC) collections show that the parameter sensitivity does remarkably decrease when query terms are reweighed. Categories and Subject Descriptors: H.3.3 [Information S...

• Type: Conference
• Year: 2007
• Where: CIKM
• Authors: Ben He, Iadh Ounis
• Keywords: CIKM 2007, Normalisation Parameter Sensitivity, Parameter Sensitivity, Query Terms