Predicting query performance, that is, the effectiveness of a search performed in response to a query, is a highly important and challenging problem. Our novel approach to addressing this challenge is based on estimating the potential amount of query drift in the result list, i.e., the presence (and dominance) of aspects or topics not related to the query in top-retrieved documents. We argue that query-drift can potentially be estimated by measuring the diversity (e.g., standard deviation) of the retrieval scores of these documents. Empirical evaluation demonstrates the prediction effectiveness of our approach for several retrieval models. Specifically, the prediction success is better, over most tested TREC corpora, than that of state-of-the-art prediction methods.

No abstract

We present a novel framework for the query-performance prediction task. That is, estimating the effectiveness of a search performed in response to a query in lack of relevance judgments. Our approach is based on using statistical decision theory for estimating the utility that a document ranking provides with respect to an information need expressed by the query. To address the uncertainty in inferring the information need, we estimate utility by the expected similarity between the given ranking and those induced by relevance models; the impact of a relevance model is based on its presumed representativeness of the information need. Specific query-performance predictors instantiated from the framework substantially outperform state-of-the-art predictors over five TREC corpora.

No abstract

The query-performance prediction task is estimating the effectiveness of a search performed in response to a query in lack of relevance judgments. Post-retrieval predictors analyze the result list of top-retrieved documents. While many of these previously proposed predictors are supposedly based on different principles, we show that they can actually be derived from a novel unified prediction framework that we propose. The framework is based on using a pseudo effective and/or ineffective ranking as reference comparisons to the ranking at hand, the quality of which we want to predict. Empirical exploration provides support to the underlying principles, and potential merits, of our framework.