This repository provides a comprehensive survey on automatic evaluation metrics for machine translation (MT), covering trends, taxonomy, key contributions, and shortcomings. We conduct experiments on representative metrics, analyze related problems, and discuss current limitations and suggestions for future research to improve MT evaluation.
@article{lee2023survey,
title={A Survey on Evaluation Metrics for Machine Translation},
author={Lee, Seungjun and Lee, Jungseob and Moon, Hyeonseok and Park, Chanjun and Seo, Jaehyung and Eo, Sugyeong and Koo, Seonmin and Lim, Heuiseok},
journal={Mathematics},
volume={11},
number={4},
pages={1006},
year={2023},
publisher={MDPI}
}