Cross-encoder Retrieval Models

Cross-Encoder Retrieval Models is a retrieval model that, as a member of the neural retrieval models family, fundamentally differs from bi-encoder approaches by jointly encoding query and document in a cross-interaction manner to compute fine-grained semantic relevance scores through deep contextualized interaction.

13

Publications

609

Citations

71

Authors

15

Institutions

Publications per year

2017–2026

13

Authors

71

  1. JL
    Jimmy Lin

    University of Waterloo, Canada

    3 publications · 173 citations

    3

    h-index

  2. SL
    Sheng-Chieh Lin

    University of Waterloo, Canada

    3 publications · 173 citations

    3

    h-index

  3. ML
    Minghan Li

    University of Waterloo, Canada

    2 publications · 54 citations

    2

    h-index

  4. JL
    Jiaxiang Liu

    Beihang University, China

    1 publications · 19 citations

    1

    h-index

  5. AA
    Akari Asai

    University of Washington, United States

    1 publications · 35 citations

    1

    h-index

1–5 of 71

Venues

  1. arXiv (Cornell University)

    Repository · 4 publications · 156 citations

    4

    h-index

  2. 1

    h-index

  3. Automation in Construction

    1 publications · 61 citations

    1

    h-index

  4. 1

    h-index

  5. Technological Forecasting and Social Change

    1 publications · 16 citations

    1

    h-index

1–5