Probing language identity encoded in pre-trained multilingual models: a typological view

Pre-trained multilingual models have been extensively used in cross-lingual information processing tasks. Existing work focuses on improving the transferring performance of pre-trained multilingual models but ignores the linguistic properties that models preserve at encoding time—“language identity”...

Descripción completa

Detalles Bibliográficos
Autores principales: Zheng, Jianyu, Liu, Ying
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2022
Materias:
Artificial Intelligence
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9044357/
https://www.ncbi.nlm.nih.gov/pubmed/35494801
http://dx.doi.org/10.7717/peerj-cs.899

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9044357/
https://www.ncbi.nlm.nih.gov/pubmed/35494801
http://dx.doi.org/10.7717/peerj-cs.899

Ejemplares similares