Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks

Natural language understanding (NLU) has made massive progress driven by large benchmarks, but benchmarks often leave a long tail of infrequent phenomena underrepresented. We reflect on the question: Have transfer learning methods sufficiently addressed the poor performance of benchmark-trained mode...

Descripción completa

Detalles Bibliográficos
Autores principales: Naik, Aakanksha, Lehman, Jill, Rosé, Carolyn
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MIT Press 2022
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9590102/
https://www.ncbi.nlm.nih.gov/pubmed/36303892
http://dx.doi.org/10.1162/tacl_a_00500

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9590102/
https://www.ncbi.nlm.nih.gov/pubmed/36303892
http://dx.doi.org/10.1162/tacl_a_00500

Ejemplares similares