RoBLEURT Submission for the WMT2021 Metrics Task
This work addresses the need for more accurate automated evaluation metrics in machine translation, offering an incremental improvement over existing methods.
The paper tackled the problem of improving trainable metrics for machine translation evaluation by proposing RoBLEURT, which achieved state-of-the-art correlations with human annotations on 8 out of 10 to-English language pairs in the WMT2020 dataset.
In this paper, we present our submission to Shared Metrics Task: RoBLEURT (Robustly Optimizing the training of BLEURT). After investigating the recent advances of trainable metrics, we conclude several aspects of vital importance to obtain a well-performed metric model by: 1) jointly leveraging the advantages of source-included model and reference-only model, 2) continuously pre-training the model with massive synthetic data pairs, and 3) fine-tuning the model with data denoising strategy. Experimental results show that our model reaching state-of-the-art correlations with the WMT2020 human annotations upon 8 out of 10 to-English language pairs.