BERTTune: Fine-Tuning Neural Machine Translation with BERTScore

Neural machine translation models are often biased toward the limited translation references seen during training. To amend this, we propose fine-tuning the models with a novel training objective based on the recently-proposed BERTScore evaluation metric.

神经机器翻译模型（Neural Machine Translation models）通常会偏向于训练过程中所见的有限翻译参考。为了修正这一问题，我们提出基于近期提出的BERTScore评估指标，以一种新颖的训练目标对模型进行微调。