Estimating query performance using class predictions

Authors:
Kevyn Collins-Thompson;Paul N. Bennett
Affiliations:
Microsoft Corporation, Redmond, WA, USA;Microsoft Corporation, Redmond, WA, USA
Venue:
Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
Year:
2009

Citing 8
Cited 4

Ranking robustness: a novel framework to predict query performance

CIKM '06 Proceedings of the 15th ACM international conference on Information and knowledge management
Query performance prediction

Information Systems
Identifying ambiguous queries in web search

Proceedings of the 16th international conference on World Wide Web
Quantify query ambiguity using ODP metadata

SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
Towards robust query expansion: model selection in the language modeling framework

SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
Quantifying query ambiguity

HLT '02 Proceedings of the second international conference on Human Language Technology Research
Improved query difficulty prediction for the web

Proceedings of the 17th ACM conference on Information and knowledge management
To swing or not to swing: learning when (not) to advertise

Proceedings of the 17th ACM conference on Information and knowledge management

Precomputing search features for fast and accurate query classification

Proceedings of the third ACM international conference on Web search and data mining
Classification-enhanced ranking

Proceedings of the 19th international conference on World wide web
A learning approach to optimizing exploration---exploitation tradeoff in relevance feedback

Information Retrieval
Combining pre-retrieval query quality predictors using genetic programming

Applied Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We investigate using topic prediction data, as a summary of document content, to compute measures of search result quality. Unlike existing quality measures such as query clarity that require the entire content of the top-ranked results, class-based statistics can be computed efficiently online, because class information is compact enough to precompute and store in the index. In an empirical study we compare the performance of class-based statistics to their language-model counterparts for predicting two measures: query difficulty and expansion risk. Our findings suggest that using class predictions can offer comparable performance to full language models while reducing computation overhead.