Probabilistic Models of Novel Document Rankings for Faceted Topic Retrieval
Ben Carterette, Praveen Chandar · 2009
Traditional models of information retrieval assume docu-ments are independently relevant. But when the goal is retrieving diverse or novel information about a topic, re-trieval models need to capture dependencies between doc-uments. Such tasks require alternative evaluation and op-timization methods that operate on different types of rel-evance judgments. We define faceted topic retrieval as a particular novelty-driven task with the goal of finding a set of documents that cover the different facets of an informa-tion need. A faceted topic retrieval system must be able to cover as many facets as possible with the smallest number of documents. We introduce two novel models for faceted topic retrieval, one based on pruning a set of retrieved documents and one based on retrieving sets of documents through di-rect optimization of evaluation measures. We compare the performance of our models to MMR and the probabilistic model due to Zhai et al. on a set of 60 topics annotated with facets, showing that our models are competitive.