Dense Vector Retrieval Models is a retrieval framework that represents queries and documents as dense, low-dimensional vectors in a continuous semantic space, enabling relevance scoring through geometric similarity measures rather than sparse term-based matching.
11
Publications
3.3K
Citations
56
Authors
15
Institutions
Publications per year
2017–2026
11
Parents
Publications
11
Authors
56
- VK
3
h-index
- PL
3
h-index
- SR
3
h-index
- HK
2
h-index
- TR
2
h-index
1–5 of 56
Institutions
15
Meta (Israel)
Tel Aviv, Israel
2 h-index
12 publications
3.2K citations
University of Pennsylvania
Philadelphia, United States
1 h-index
2 publications
122 citations
Chinese Academy of Sciences
Beijing, China
1 h-index
2 publications
52 citations
Microsoft Research (United Kingdom)
Cambridge, United Kingdom
1 h-index
7 publications
322 citations
Astana Medical University
Nur-Sultan, Kazakhstan
1 h-index
3 publications
135 citations
Institute of Software
Beijing, China
1 h-index
2 publications
52 citations
New York University
New York, United States
1 h-index
1 publications
18 citations
University of Glasgow
Glasgow, United Kingdom
1 h-index
1 publications
26 citations
1–8 of 15
Venues
- arXiv (Cornell University)
Repository · 2 publications · 3.1K citations
2
h-index
- Transactions of the Association for Computational Linguistics
TACL · 1 publications · 19 citations
1
h-index
- Big Data and Cognitive Computing
1 publications · 45 citations
1
h-index
- Findings of the Association for Computational Linguistics: NAACL 2022
Conference · 1 publications · 40 citations
1
h-index
- UCL Discovery (University College London)
Repository · 1 publications · 18 citations
1
h-index
1–5