Accelerated Query Processing Via Similarity Score Prediction

Petri, M, Moffat, A, Mackenzie, J, Culpepper, J and Beck, D 2019, 'Accelerated Query Processing Via Similarity Score Prediction', in Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2019), Paris, France, 21 - 25 July 2019, pp. 485-494.


Document type: Conference Paper
Collection: Conference Papers

Title Accelerated Query Processing Via Similarity Score Prediction
Author(s) Petri, M
Moffat, A
Mackenzie, J
Culpepper, J
Beck, D
Year 2019
Conference name SIGIR 2019: Session 5B: Efficiency, Effectiveness and Performance
Conference location Paris, France
Conference dates 21 - 25 July 2019
Proceedings title Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2019)
Publisher Association for Computing Machinery
Place of publication New York, United States
Start page 485
End page 494
Total pages 10
Abstract Processing top-k bag-of-words queries is critical to many information retrieval applications, including web-scale search. In this work, we consider algorithmic properties associated with dynamic pruning mechanisms. Such algorithms maintain a score threshold (the k th highest similarity score identified so far) so that low-scoring documents can be bypassed, allowing fast top-k retrieval with no loss in effectiveness. In standard pruning algorithms the score threshold is initialized to the lowest possible value. To accelerate processing, we make use of term- and query-dependent features to predict the final value of that threshold, and then employ the predicted value right from the commencement of processing. Because of the asymmetry associated with prediction errors (if the estimated threshold is too high the query will need to be re-executed in order to assure the correct answer), the prediction process must be risk-sensitive. We explore techniques for balancing those factors, and provide detailed experimental results that show the practical usefulness of the new approach.
Subjects Information Retrieval and Web Search
Keyword(s) Inverted index
query efficiency
dynamic pruning
information retrieval
DOI - identifier 10.1145/3331184.3331207
Copyright notice Copyright © 2019 by the Association for Computing Machinery, Inc. (ACM).
ISBN 9781450361729
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Altmetric details:
Access Statistics: 37 Abstract Views  -  Detailed Statistics
Created: Wed, 23 Oct 2019, 08:59:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us