Efficient & Effective Selective Query Rewriting with Efficiency Predictions
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-05328
- Type
- E - Conference contribution
- DOI
-
10.1145/3077136.3080827
- Title of conference / published proceedings
- SIGIR 2017: The 40th International ACM SIGIR Conference on Research and Development in Information Retrieval
- First page
- 495
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- August
- Year of publication
- 2017
- URL
-
http://eprints.gla.ac.uk/142932/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- ORIGINALITY: Describes a technique for adjusting underlying query formulation within a search engine depending on the predicted time that the query will take to execute. Allows efficient (fast) retrieval while minimising effectiveness degradation (accuracy of results), ensuring that users are satisfied, while reducing required computing resources. RIGOUR: Evaluated with real user queries on the largest NIST dataset (50M documents). SIGNIFICANCE: Published in premier IR conference. Our approach demonstrates 62% decrease in tail, (i.e., 95th-percentile) response time without significant degradation in effectiveness; Another application of the query efficiency prediction techniques behind the [removed for publication] Macdonald and Ounis REF2021 impact case-study.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -