Dense Retrieval
Dense Retrieval is a retrieval paradigm within information retrieval that employs dense vector representations of queries and documents, derived through learned embedding models, to capture semantic similarity in a continuous vector space, distinguishing it from sparse retrieval approaches that rely on lexical term-based matching.
146
Publications
15.4K
Citations
419
Authors
116
Institutions
Publications per year
2017–2026
144
146
A vector space model for automatic indexing
Gerard Salton, Anita M.-Y. Wong, Chul‐Su Yang · Communications of the ACM · 1975 · 7.4K citations · Full text
1–5 of 146
419
15
h-index
11
h-index
9
h-index
8
h-index
8
h-index
1–5 of 419
116

Renmin University of China
Beijing, China
15 h-index
39 publications
4K citations

University of Waterloo
Waterloo, Canada
12 h-index
35 publications
3.1K citations
Tsinghua University
Beijing, China
11 h-index
38 publications
2.2K citations
Microsoft Research (United Kingdom)
Cambridge, United Kingdom
9 h-index
30 publications
3.9K citations
University of Chinese Academy of Sciences
Beijing, China
9 h-index
29 publications
893 citations
Microsoft (United States)
Redmond, United States
8 h-index
18 publications
1K citations

The University of Queensland
Brisbane, Australia
8 h-index
22 publications
679 citations

University of Glasgow
Glasgow, United Kingdom
7 h-index
15 publications
670 citations
1–8 of 116
Repository · 37 publications · 1.6K citations
22
h-index
Conference · 9 publications · 422 citations
9
h-index
Conference · 8 publications · 402 citations
8
h-index
TACL · 3 publications · 343 citations
3
h-index
Conference · 2 publications · 43 citations
2
h-index
1–5