https://www.amazon.science/publications/gemv2-multilingual-nlg-benchmarking-in-a-single-line-of-code
GEMv2: Multilingual NLG benchmarking in a single line of code - Amazon Science
Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. The...
a single line of code
https://arxiv.org/abs/2206.11249v3
[2206.11249v3] GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
Abstract page for arXiv paper 2206.11249v3: GEMv2: Multilingual NLG Benchmarking in a Single Line of Code