English

The Cost of Training NLP Models: A Concise Overview

Computation and Language 2020-04-21 v1 Machine Learning Neural and Evolutionary Computing

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).

Keywords

Cite

@article{arxiv.2004.08900,
  title  = {The Cost of Training NLP Models: A Concise Overview},
  author = {Or Sharir and Barak Peleg and Yoav Shoham},
  journal= {arXiv preprint arXiv:2004.08900},
  year   = {2020}
}
R2 v1 2026-06-23T14:57:02.198Z