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

Authors

419

  1. JL
    Jimmy Lin

    University of Waterloo, Canada

    20 publications · 1.1K citations

    15

    h-index

  2. XM
    Xueguang Ma

    University of Waterloo, Canada

    11 publications · 794 citations

    11

    h-index

  3. CX
    Chenyan Xiong

    Carnegie Mellon University, United States

    9 publications · 760 citations

    9

    h-index

  4. JC
    Jamie Callan

    Carnegie Mellon University, United States

    8 publications · 554 citations

    8

    h-index

  5. JM
    Jiaxin Mao

    Tsinghua University, China

    8 publications · 451 citations

    8

    h-index

1–5 of 419

Venues

  1. arXiv (Cornell University)

    Repository · 37 publications · 1.6K citations

    22

    h-index

  2. 9

    h-index

  3. 8

    h-index

  4. 3

    h-index

  5. 2

    h-index

1–5