Neural Query Performance Prediction using Weak Supervision from Multiple Signals

Zamani, H, Croft, W and Culpepper, J 2018, 'Neural Query Performance Prediction using Weak Supervision from Multiple Signals', in Claudia Hauff & Craig Macdonald (ed.) Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, Ann Arbor, MI, USA, July 08 - 12 2018, pp. 105-114.


Document type: Conference Paper
Collection: Conference Papers

Title Neural Query Performance Prediction using Weak Supervision from Multiple Signals
Author(s) Zamani, H
Croft, W
Culpepper, J
Year 2018
Conference name The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval 2018
Conference location Ann Arbor, MI, USA
Conference dates July 08 - 12 2018
Proceedings title Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval
Editor(s) Claudia Hauff & Craig Macdonald
Publisher ACM
Place of publication New York
Start page 105
End page 114
Total pages 10
Abstract Predicting the performance of a search engine for a given query is a fundamental and challenging task in information retrieval. Accurate performance predictors can be used in various ways, such as triggering an action, choosing the most effective ranking function per query, or selecting the best variant from multiple query formulations. In this paper, we propose a general end-to-end query performance prediction framework based on neural networks, called NeuralQPP. Our framework consists of multiple components, each learning a representation suitable for performance prediction. These representations are then aggregated and fed into a prediction sub-network. We train our models with multiple weak supervision signals, which is an unsupervised learning approach that uses the existing unsupervised performance predictors using weak labels. We also propose a simple yet effective component dropout technique to regularize our model. Our experiments on four newswire and web collections demonstrate that NeuralQPP significantly outperforms state-of-the-art baselines, in nearly every case. Furthermore, we thoroughly analyze the effectiveness of each component, each weak supervision signal, and all resulting combinations in our experiments.
Subjects Data Structures
Information Retrieval and Web Search
DOI - identifier 10.1145/3209978.3210041
Copyright notice © 2018 Association for Computing Machinery.
ISBN 9781450356572
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 7 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 16 Abstract Views  -  Detailed Statistics
Created: Tue, 26 Mar 2019, 09:36:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us