The Cost of Training NLP Models: A Concise Overview

Computer Science > Computation and Language

arXiv:2004.08900 (cs)

[Submitted on 19 Apr 2020]

Title:The Cost of Training NLP Models: A Concise Overview

Authors:Or Sharir, Barak Peleg, Yoav Shoham

Download PDF

Abstract: We review the cost of training large-scale language models, and the drivers of these costs. The intended audience includes engineers and scientists budgeting their model-training experiments, as well as non-practitioners trying to make sense of the economics of modern-day Natural Language Processing (NLP).

Subjects:	Computation and Language (cs.CL); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
Cite as:	arXiv:2004.08900 [cs.CL]
	(or arXiv:2004.08900v1 [cs.CL] for this version)

Submission history

From: Or Sharir [view email]
[v1] Sun, 19 Apr 2020 16:28:35 UTC (328 KB)

from Hacker News https://ift.tt/2VqAQhO