Universal Sentence Representations

Universal Sentence Representations is a framework in natural language processing that belongs to the class of sentence representation models and is distinguished by its ability to encode diverse linguistic information into fixed-dimensional vector spaces through self-supervised learning, enabling broad transferability across downstream tasks.

84

Publications

10.5K

Citations

287

Authors

116

Institutions

Publications per year

2017–2026

74

Variants

Usr

Authors

287

  1. DC
    Daniel Cer

    Google (United States), United States

    6 publications · 3.1K citations

    6

    h-index

  2. AC
    Alexis Conneau

    Meta (Israel), Israel

    6 publications · 3.9K citations

    6

    h-index

  3. HS
    Holger Schwenk

    Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur, France

    5 publications · 3.3K citations

    5

    h-index

  4. YY
    Yinfei Yang

    Google (United States), United States

    5 publications · 3.1K citations

    5

    h-index

  5. RK
    Ray Kurzweil

    Google (United States), United States

    4 publications · 3K citations

    4

    h-index

1–5 of 287

Venues

  1. arXiv (Cornell University)

    Repository · 15 publications · 4.7K citations

    13

    h-index

  2. IEEE Access

    4 publications · 208 citations

    4

    h-index

  3. Arabian Journal for Science and Engineering

    1 publications · 23 citations

    2

    h-index

  4. 2

    h-index

  5. Knowledge-Based Systems

    2 publications · 83 citations

    2

    h-index

1–5