Estimating the query difficulty for information retrieval

cover image

Where to find it

Information & Library Science Library

Call Number
ZA4230 .C37 2010
Status
Available

Authors, etc.

Names:

Summary

Many information retrieval (IR) systems suffer from a radical variance in performance when responding to users' queries. Even for systems that succeed very well on average, the quality of results returned for some of the queries is poor. Thus, it is desirable that IR systems will be able to identify ""difficult"" queries so they can be handled properly. Understanding why some queries are inherently more difficult than others is essential for IR, and a good answer to this important question will help search engines to reduce the variance in performance, hence better servicing their customer needs. Estimating the query difficulty is an attempt to quantify the quality of search results retrieved for a query from a given collection of documents. This book discusses the reasons that cause search engines to fail for some of the queries, and then reviews recent approaches for estimating query difficulty in the IR field. It then describes a common methodology for evaluating the prediction quality of those estimators, and experiments with some of the predictors applied by various IR methods over several TREC benchmarks. Finally, it discusses potential applications that can utilize query difficulty estimators by handling each query individually and selectively, based upon its estimated difficulty.

Contents

1. Introduction: the robustness problem of information retrieval -- Reasons for retrieval failures, the RIA workshop -- Instability in retrieval, the TREC's robust tracks -- Estimating the query difficulty -- Summary

2. Basic concepts -- The retrieval task -- The prediction task -- Linear correlation -- Rank correlation -- Prediction robustness -- Summary

4. Pre-retrieval prediction methods -- Linguistic approaches -- Statistical approaches -- Definitions -- Specificity -- Similarity -- Coherency -- Term relatedness -- Evaluating pre-retrieval methods -- Summary

5. Post-retrieval prediction methods -- Clarity -- Definition -- Examples -- Other clarity measures -- Robustness -- Query perturbation -- Document perturbation -- Retrieval perturbation -- Cohesion -- Score distribution analysis -- Evaluating post-retrieval methods -- Prediction sensitivity -- Summary

6. Combining predictors -- Linear regression -- Combining pre-retrieval predictors -- Combining post-retrieval predictors -- Combining predictors based on statistical decision theory -- Evaluating the UEF framework -- Results -- Combining predictors in the UEF model -- Summary

7. A general model for query difficulty -- Geometrical illustration -- General model -- Validating the general model -- The relationship between aspect coverage and query difficulty -- Validating the relationship between aspect coverage and query difficulty -- Summary

8. Applications of query difficulty estimation -- Feedback: to the user and to the system -- Federation and metasearch -- Content enhancement using missing content analysis -- Selective query expansion -- Selective expansion based on query drift estimation -- Adaptive use of pseudo relevance feedback -- Other uses of query difficulty prediction -- Summary

9. Summary and conclusions -- Summary -- What next -- Concluding remarks -- Bibliography -- Authors' biographies.

Other details