Cross-lingual Transfer Learning

Cross-Lingual Transfer Learning is a machine learning paradigm in which knowledge acquired from a source language model is leveraged to improve performance in a target language model, enabling effective natural language processing across linguistic boundaries.

692

Publications

37.6K

Citations

1.9K

Authors

460

Institutions

Publications per year

2017–2026

533

Authors

1.9K

  1. IV
    Ivan Vulić

    University of Cambridge, United Kingdom

    28 publications · 2K citations

    20

    h-index

  2. GG
    Goran Glavašš

    University of Mannheim, Germany

    21 publications · 908 citations

    16

    h-index

  3. FW
    Furu Wei

    Microsoft Research Asia (China), China

    19 publications · 932 citations

    15

    h-index

  4. GN
    Graham Neubig

    Carnegie Mellon University, United States

    18 publications · 1.5K citations

    14

    h-index

  5. AK
    Anna Korhonen

    University of Cambridge, United Kingdom

    13 publications · 661 citations

    13

    h-index

1–5 of 1.9K

Venues

  1. arXiv (Cornell University)

    Repository · 94 publications · 4.7K citations

    32

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 24 publications · 883 citations

    17

    h-index

  3. 15

    h-index

  4. 12

    h-index

  5. 9

    h-index

1–5