Efficient & Effective Selective Query Rewriting with Efficiency Predictions

Craig Macdonald, Nicola Tonellotto, Iadh Ounis
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
To enhance e ectiveness, a user's query can be rewri en internally by the search engine in many ways, for example by applying proximity, or by expanding the query with related terms. However, approaches that bene t e ectiveness o en have a negative impact on e ciency, which has impacts upon the user satisfaction, if the query is excessively slow. In this paper, we propose a novel framework for using the predicted execution time of various query rewritings to select between alternatives on a
more » ... ternatives on a per-query basis, in a manner that ensures both e ectiveness and e ciency. In particular, we propose the prediction of the execution time of ephemeral (e.g., proximity) posting lists generated from uni-gram inverted index posting lists, which are used in establishing the permissible query rewriting alternatives that may execute in the allowed time. Experiments examining both the e ectiveness and e ciency of the proposed approach demonstrate that a 49% decrease in mean response time (and 62% decrease in 95th-percentile response time) can be a ained without signi cantly hindering the e ectiveness of the search engine.
doi:10.1145/3077136.3080827 dblp:conf/sigir/MacDonaldTO17 fatcat:5ai4wudqbnap5n4ft5wkhhtjze