Results of WMT22 Metrics Shared Task: Stop Using BLEU – Neural Metrics Are Better and More Robust

Results of WMT22 Metrics Shared Task: Stop Using BLEU – Neural Metrics Are Better and More Robust Markus Freitag author Ricardo Rei author Nitika Mathur author Chi-kiu Lo author Craig Stewart author Eleftherios Avramidis author Tom Kocmi author George Foster author Alon Lavie author André F T Martins author 2022-12 text Proceedings of the Seventh Conference on Machine Translation (WMT) Philipp Koehn editor Loïc Barrault editor Ondřej Bojar editor Fethi Bougares editor Rajen Chatterjee editor Marta R Costa-jussà editor Christian Federmann editor Mark Fishel editor Alexander Fraser editor Markus Freitag editor Yvette Graham editor Roman Grundkiewicz editor Paco Guzman editor Barry Haddow editor Matthias Huck editor Antonio Jimeno Yepes editor Tom Kocmi editor André Martins editor Makoto Morishita editor Christof Monz editor Masaaki Nagata editor Toshiaki Nakazawa editor Matteo Negri editor Aurélie Névéol editor Mariana Neves editor Martin Popel editor Marco Turchi editor Marcos Zampieri editor Association for Computational Linguistics Abu Dhabi, United Arab Emirates (Hybrid) conference publication freitag-etal-2022-results 10.18653/v1/2022.wmt-1.2 https://aclanthology.org/2022.wmt-1.2/ 2022-12 46 68