@inproceedings{collins-thompson2010predicting,
author = {Collins-Thompson, Kevyn and Bennett, Paul},
title = {Predicting Query Performance via Classification},
booktitle = {Proceedings of the 32nd Annual European Conference on Information Retrieval (ECIR 2010)},
year = {2010},
month = {March},
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 two performance-related tasks: predicting query difficulty and expansion risk. Our findings suggest that using class predictions can offer comparable performance to full language models while reducing computation overhead.},
publisher = {Springer},
url = {http://approjects.co.za/?big=en-us/research/publication/predicting-query-performance-via-classification/},
edition = {Proceedings of the 32nd Annual European Conference on Information Retrieval (ECIR 2010)},
}