Offline Pseudo Relevance Feedback for Efficient and Effective Single-pass Dense Retrieval

TL;DR

This paper introduces an offline pseudo relevance feedback method for single-pass dense retrieval, significantly reducing online latency while maintaining high effectiveness, by pre-generating pseudo-queries for faster retrieval.

Contribution

It proposes a novel offline PRF framework that shifts the feedback process offline, enabling faster online dense retrieval without sacrificing effectiveness.

Findings

Effective on TREC DL and HARD datasets

Reduces online latency by shifting PRF offline

Maintains high retrieval effectiveness

Abstract

Dense retrieval has made significant advancements in information retrieval (IR) by achieving high levels of effectiveness while maintaining online efficiency during a single-pass retrieval process. However, the application of pseudo relevance feedback (PRF) to further enhance retrieval effectiveness results in a doubling of online latency. To address this challenge, this paper presents a single-pass dense retrieval framework that shifts the PRF process offline through the utilization of pre-generated pseudo-queries. As a result, online retrieval is reduced to a single matching with the pseudo-queries, hence providing faster online retrieval. The effectiveness of the proposed approach is evaluated on the standard TREC DL and HARD datasets, and the results demonstrate its promise. Our code is openly available at https://github.com/Rosenberg37/OPRF.