Clustering-Based Methods for Vector-Based Pseudo-Relevance Feedback
TL;DR
This work aims to explore how well vector-based pseudo relevance feedback can adapt to dense retrieval models when it is not feasible to use surface-form information to pick discriminating expansion tokens.
Abstract
Prior work has shown that vector-based pseudo relevance feedback (PRF) is an effective technique for query expansion for improving retrieval results in dense information retrieval. In dense retrieval, ColBERT-PRF has emerged as a novel mechanism, using cluster centroids built from feedback documents as PRF expansion tokens and leveraging statistical information from the closest neighboring token ids to dictate how useful these expansion tokens are. While this approach has been shown to work well in the monolingual retrieval setting for English using the original ColBERT infrastructure, such systems have since evolved to improve inference speed, reduce storage and memory usage, and support cross-language (CLIR) and multilingual (MLIR) retrieval. As a result, many of these advancements have reduced the ability to utilize token-level statistics. In this work, we aim to explore how well this type of approach can adapt to dense retrieval models when it is not feasible to use surface-form information to pick discriminating expansion tokens. Furthermore, we explore alternative clustering mechanisms, such as HDBScan, to compare how different clustering methods perform at building clusters that can be useful for PRF. Experiments on MLIR, CLIR, and Report Generation tasks, such as those in the TREC 2024 NeuCLIR Report Generation Pilot Task, show that even without access to these token statistics, the use of cluster centroids for PRF can still improve nDCG and α-nDCG by up to 12%.