Towards Efficient and Effective Query Variant Generation

Benham, R, Culpepper, J, Gallagher, L, Lu, X and Mackenzie, J 2018, 'Towards Efficient and Effective Query Variant Generation', in Omar Alonso and Gianmaria Silvello (ed.) Proceedings of the First Biennial Conference on Design of Experimental Search and Information Retrieval Systems (DESIRES 2018), Bertinoro, Italy, 28-31 August 2018, pp. 62-67.


Document type: Conference Paper
Collection: Conference Papers

Title Towards Efficient and Effective Query Variant Generation
Author(s) Benham, R
Culpepper, J
Gallagher, L
Lu, X
Mackenzie, J
Year 2018
Conference name DESIRES 2018
Conference location Bertinoro, Italy
Conference dates 28-31 August 2018
Proceedings title Proceedings of the First Biennial Conference on Design of Experimental Search and Information Retrieval Systems (DESIRES 2018)
Editor(s) Omar Alonso and Gianmaria Silvello
Publisher Rheinisch-Westfaelische Technische Hochschule Aachen * Lehrstuhl Informatik V
Place of publication Germany
Start page 62
End page 67
Total pages 6
Abstract Relevance modeling and data fusion are powerful yet simple approaches to improving the effectiveness of Information Retrieval Systems. For many of the classic TREC test collections, these approaches were used in many of the top performing retrieval systems. However, these approaches are often inefficient and are therefore rarely applied in production systems which must adhere to strict performance guarantees. Inspired by our recent work with human derived query variations, we propose a new sampling-based system which provides significantly better efficiency-effectiveness tradeoffs while leveraging both relevance modeling and data fusion. We show that our new end-to-end search system approaches the state-of-the-art in effectiveness while still being efficient in practice. Orthogonally, we also show how to leverage query expansion and data fusion to achieve significantly better risk-reward trade-offs than plain relevance modeling approaches.
Subjects Data Structures
Information Retrieval and Web Search
Keyword(s) Information Retrieval
Copyright notice © 2018 Copyright held by the author(s). Creative Commons CC0
ISSN 1613-0073
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Access Statistics: 30 Abstract Views  -  Detailed Statistics
Created: Fri, 14 Dec 2018, 16:06:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us