Sparse Retrieval
Sparse Retrieval is a retrieval paradigm within information retrieval that operates on high-dimensional, sparsely populated representations—typically term-based vector spaces—where matching is determined by exact or weighted term overlap, distinguishing it from dense retrieval approaches that rely on continuous, low-dimensional embeddings to capture semantic similarity.
79
Publications
4.8K
Citations
271
Authors
99
Institutions
Publications per year
2017–2026
55
Variants
Sparse Information Retrieval
79
1–5 of 79
271
9
h-index
6
h-index
4
h-index
4
h-index
3
h-index
1–5 of 271
99

University of Waterloo
Waterloo, Canada
7 h-index
16 publications
2.3K citations

Chinese Academy of Sciences
Beijing, China
5 h-index
10 publications
239 citations

Renmin University of China
Beijing, China
5 h-index
18 publications
792 citations

University of Pisa
Pisa, Italy
4 h-index
4 publications
171 citations

The University of Queensland
Brisbane, Australia
4 h-index
8 publications
171 citations
Google (United States)
Mountain View, United States
3 h-index
11 publications
1.5K citations
Technion – Israel Institute of Technology
Haifa, Israel
3 h-index
6 publications
494 citations
Microsoft Research (United Kingdom)
Cambridge, United Kingdom
3 h-index
15 publications
2.9K citations
1–8 of 99
Repository · 9 publications · 604 citations
9
h-index
Conference · 3 publications · 179 citations
3
h-index
Conference · 3 publications · 138 citations
3
h-index
2 publications · 167 citations
2
h-index
2 publications · 23 citations
2
h-index
1–5