-
COMET: A neural framework for MT evaluation
The COMET dataset contains human-annotated scores for machine translation candidates. -
WMT2020 Metrics Shared Task
The WMT2020 Metrics Shared Task dataset contains human-annotated scores for machine translation candidates. -
RoBLEURT Submission for the WMT2021 Metrics Task
RoBLEURT is a robustly optimizing the training of BLEURT, a trainable metric model for evaluating the semantic consistency between machine translation candidates and golden...