← smac.pub home

A Deep Learning Approach for Selective Relevance Feedback

pdf bibtex long conference paper

Authors: Suchana Datta, Debasis Ganguly, Sean MacAvaney, Derek Greene

Appeared in: Proceedings of the 46th European Conference on Information Retrieval Research (ECIR 2024)

DOI 10.1007/978-3-031-56060-6_13 DBLP conf/ecir/DattaGMG24 arXiv 2401.11198 Google Scholar 7wWfoDgAAAAJ:M05iB0D1s5AC Semantic Scholar 0cfa9e7d53c890488b8501e543e27a6ee7d5014c Enlighten 312863 smac.pub ecir2024-adprf


Pseudo-relevance feedback (PRF) can enhance average retrieval effectiveness over a sufficiently large number of queries. However, PRF often introduces a drift into the original information need, thus hurting the retrieval effectiveness of several queries. While a selective application of PRF can potentially alleviate this issue, previous approaches have largely relied on unsupervised or feature-based learning to determine whether a query should be expanded. In contrast, we revisit the problem of selective PRF from a deep learning perspective, presenting a model that is entirely data-driven and trained in an end-to-end manner. The proposed architecture leverages a transformer-based bi-encoder architecture. Additionally, to further improve retrieval effectiveness with this selective PRF approach, we make use of the model's confidence estimates to combine the information from the original and expanded queries. In our experiments, we apply this selective feedback on a number of different combinations of ranking and feedback models, and show that our proposed approach consistently improves retrieval effectiveness for both sparse and dense ranking models, with the feedback models being either sparse, dense or generative.

BibTeX @inproceedings{datta:ecir2024-adprf, author = {Datta, Suchana and Ganguly, Debasis and MacAvaney, Sean and Greene, Derek}, title = {A Deep Learning Approach for Selective Relevance Feedback}, booktitle = {Proceedings of the 46th European Conference on Information Retrieval Research}, year = {2024}, url = {https://arxiv.org/abs/2401.11198}, doi = {10.1007/978-3-031-56060-6_13} }