skip to main content
LOTERRE

LOTERRE

Search from vocabulary

Content language

| español français
Search help

Concept information

Preferred term

PIXEL  

Definition(s)

  • "PIXEL is a pretrained language model that renders text as images, making it possible to transfer representations across languages based on orthographic similarity or the co-activation of pixels." (Rust et al., 2022).

Broader concept(s)

Synonym(s)

  • pixel-based encoders of language

Bibliographic citation(s)

  • • Rust, P., Lotz, J. F., Bugliarello, E., Salesky, E., de Lhoneux, M., & Elliott, D. (2022). Language modelling with pixels (arXiv:2207.06991). arXiv. doi:10.48550/arXiv.2207.06991

has application field

has design country

  • Belgium
  • Danemark
  • Sweden
  • United States

has for input language

documentation URL

implements

is encoded in

In other languages

  • French

  • pixel-based encoders of language

URI

http://data.loterre.fr/ark:/67375/LTK-MCP9KCHH-6

Download this concept:

RDF/XML TURTLE JSON-LD Last modified 6/20/24