Deep-QPP: a Pairwise Interaction-based Deep Learning Model for Supervised Query Performance Prediction

Datta, S., Ganguly, D. , Greene, D. and Mitra, M. (2022) Deep-QPP: a Pairwise Interaction-based Deep Learning Model for Supervised Query Performance Prediction. In: WSDM '22: 15th ACM International Conference on Web Search and Data Mining, 21-25 Feb 2022, pp. 201-209. ISBN 9781450391320

Abstract

Motivated by the recent success of end-to-end deep neural models for ranking tasks, we present here a supervised end-to-end neural approach for query performance prediction (QPP). In contrast to unsupervised approaches that rely on various statistics of document score distributions, our approach is entirely data-driven. Further, in contrast to weakly supervised approaches, our method also does not rely on the outputs from different QPP estimators. In particular, our model leverages information from the semantic interactions between the terms of a query and those in the top-documents retrieved with it. The architecture of the model comprises multiple layers of 2D convolution filters followed by a feed-forward layer of parameters. Experiments on standard test collections demonstrate that our proposed supervised approach outperforms other state-of-the-art supervised and unsupervised approaches.

• Item Type: Conference Proceedings
• Keywords: Supervised query performance prediction, interaction-based models, convolutional neural networks.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Ganguly, Dr Debasis
• Authors: Datta, S., Ganguly, D., Greene, D., and Mitra, M.
• Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
• College/School: College of Science and Engineering > School of Computing Science
• Research Group: IDA
• ISBN: 9781450391320
• Published Online: 15 February 2022
• Copyright Holders: Copyright © 2022 The Authors
• First Published: First published in Proceedings of the 15th ACM International Conference on Web Search and Data Mining (WSDM '22): 201-209
• Publisher Policy: Reproduced in accordance with the publisher copyright policy

Related URLs

• Organisation