How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation — mentioned by potatoman22

Sat, 22 Apr 2023 21:59:12 GMT

Few-shot learning typically works slightly better than zero-shot learning. Look at tables 3 & 4 in this paper: https://arxiv.org/pdf/2302.09210.pdf

Paper and discussion history. A mention is not an endorsement.

How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation · HackerPapers discussions