Lexically-Accelerated Dense Retrieval

Kulkarni, H., MacAvaney, S. , Goharian, N. and Frieder, O. (2023) Lexically-Accelerated Dense Retrieval. In: 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR23), Taipei, Taiwan, 23-27 July 2023, pp. 152-162. ISBN 9781450394086 (doi: 10.1145/3539618.3591715)

[img] Text
296333.pdf - Accepted Version

936kB

Abstract

Retrieval approaches that score documents based on learned dense vectors (i.e., dense retrieval) rather than lexical signals (i.e., conventional retrieval) are increasingly popular. Their ability to identify related documents that do not necessarily contain the same terms as those appearing in the user's query (thereby improving recall) is one of their key advantages. However, to actually achieve these gains, dense retrieval approaches typically require an exhaustive search over the document collection, making them considerably more expensive at query-time than conventional lexical approaches. Several techniques aim to reduce this computational overhead by approximating the results of a full dense retriever. Although these approaches reasonably approximate the top results, they suffer in terms of recall -- one of the key advantages of dense retrieval. We introduce 'LADR' (Lexically-Accelerated Dense Retrieval), a simple-yet-effective approach that improves the efficiency of existing dense retrieval models without compromising on retrieval effectiveness. LADR uses lexical retrieval techniques to seed a dense retrieval exploration that uses a document proximity graph. Through extensive experiments, we find that LADR establishes a new dense retrieval effectiveness-efficiency Pareto frontier among approximate k nearest neighbor techniques. When tuned to take around 8ms per query in retrieval latency on our hardware, LADR consistently achieves both precision and recall that are on par with an exhaustive search on standard benchmarks. Importantly, LADR accomplishes this using only a single CPU -- no hardware accelerators such as GPUs -- which reduces the deployment cost of dense retrieval systems.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:MacAvaney, Dr Sean
Authors: Kulkarni, H., MacAvaney, S., Goharian, N., and Frieder, O.
College/School:College of Science and Engineering > School of Computing Science
Research Centre:College of Science and Engineering > School of Computing Science > IDA Section > GPU Cluster
ISBN:9781450394086
Copyright Holders:Copyright © 2023 held by the owner/author(s)
First Published:First published in SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval
Publisher Policy:Reproduced in accordance with the publisher copyright policy
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record