Generative Dense Retrieval: Memory Can Be a Burden

Peiwen Yuan, Xinglin Wang, Shaoxiong Feng, Boyuan Pan, Yiwei Li, Heda Wang, Xupeng Miao, Kan Li


Abstract
Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR implicitly achieves deep interaction between query and document. However, such a memorizing mechanism faces three drawbacks: (1) Poor memory accuracy for fine-grained features of documents; (2) Memory confusion gets worse as the corpus size increases; (3) Huge memory update costs for new documents. To alleviate these problems, we propose the Generative Dense Retrieval (GDR) paradigm. Specifically, GDR first uses the limited memory volume to achieve inter-cluster matching from query to relevant document clusters. Memorizing-free matching mechanism from Dense Retrieval (DR) is then introduced to conduct fine-grained intra-cluster matching from clusters to relevant documents. The coarse-to-fine process maximizes the advantages of GR’s deep interaction and DR’s scalability. Besides, we design a cluster identifier constructing strategy to facilitate corpus memory and a cluster-adaptive negative sampling strategy to enhance the intra-cluster mapping ability. Empirical results show that GDR obtains an average of 3.0 R@100 improvement on NQ dataset under multiple settings and has better scalability.
Anthology ID:
2024.eacl-long.173
Volume:
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2835–2845
Language:
URL:
https://aclanthology.org/2024.eacl-long.173
DOI:
Bibkey:
Cite (ACL):
Peiwen Yuan, Xinglin Wang, Shaoxiong Feng, Boyuan Pan, Yiwei Li, Heda Wang, Xupeng Miao, and Kan Li. 2024. Generative Dense Retrieval: Memory Can Be a Burden. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2835–2845, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Generative Dense Retrieval: Memory Can Be a Burden (Yuan et al., EACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.eacl-long.173.pdf
Note:
 2024.eacl-long.173.note.zip
Video:
 https://aclanthology.org/2024.eacl-long.173.mp4