Semantic Scholar Open Access 2022 149 sitasi

Efficient Methods for Natural Language Processing: A Survey

Marcos Vinícius Treviso Tianchu Ji Ji-Ung Lee Betty van Aken Qingqing Cao +14 lainnya

Abstrak

Abstract Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance means that resource consumption also grows. Such resources include data, time, storage, or energy, all of which are naturally limited and unevenly distributed. This motivates research into efficient methods that require fewer resources to achieve similar results. This survey synthesizes and relates current methods and findings in efficient NLP. We aim to provide both guidance for conducting NLP under limited resources, and point towards promising research directions for developing more efficient methods.

Topik & Kata Kunci

Penulis (19)

M

Marcos Vinícius Treviso

T

Tianchu Ji

J

Ji-Ung Lee

B

Betty van Aken

Q

Qingqing Cao

M

Manuel R. Ciosici

M

Michael Hassid

K

Kenneth Heafield

S

Sara Hooker

P

Pedro Henrique Martins

A

André F. T. Martins

J

Jessica Zosa Forde

P

Peter Milder

C

Colin Raffel

E

Edwin Simpson

N

N. Slonim

N

Niranjan Balasubramanian

L

Leon Derczynski

R

Roy Schwartz

Format Sitasi

Treviso, M.V., Ji, T., Lee, J., Aken, B.v., Cao, Q., Ciosici, M.R. et al. (2022). Efficient Methods for Natural Language Processing: A Survey. https://doi.org/10.1162/tacl_a_00577

Akses Cepat

Lihat di Sumber doi.org/10.1162/tacl_a_00577
Informasi Jurnal
Tahun Terbit
2022
Bahasa
en
Total Sitasi
149×
Sumber Database
Semantic Scholar
DOI
10.1162/tacl_a_00577
Akses
Open Access ✓