IR Evaluation and Learning in the Presence of Forbidden Documents

Many IR collections contain forbidden documents (F-docs), i.e. documents that should not be retrieved to the searcher. In an ideal scenario F-docs are clearly flagged, hence the ranker can filter them out, guaranteeing that no F-doc will be exposed. However, in real-world scenarios, filtering algorithms are prone to errors. Therefore, an IR evaluation system should also measure filtering quality in addition to ranking quality. Typically, filtering is considered as a classification task and is evaluated independently of the ranking quality. However, due to the mutual affinity between the two, it is desirable to evaluate ranking quality while filtering decisions are being made. In this work we propose nDCGf, a novel extension of the nDCGmin metric[14], which measures both ranking and filtering quality of the search results. We show both theoretically and empirically that while nDCGmin is not suitable for the simultaneous ranking and filtering task, nDCGf is a reliable metric in this case.