Neural machine translation models are often biased toward the limited
translation references seen during training. To amend this form of overfitting,
in this paper we propose fine-tuning the models with a novel training objective
based on the recently-proposed BERTScore evaluation metric. BERTScore is a
scoring function based on contextual embeddings that overcomes the typical
limitations of n-gram-based metrics (e.g. synonyms, paraphrases), allowing
translations that are different from the references, yet close in the
contextual embedding space, to be treated as substantially correct. To be able
to use BERTScore as a training objective, we propose three approaches for
generating soft predictions, allowing the network to remain completely
differentiable end-to-end. Experiments carried out over four, diverse language
pairs have achieved improvements of up to 0.58 pp (3.28%) in BLEU score and up
to 0.76 pp (0.98%) in BERTScore (F_BERT) when fine-tuning a strong baseline.

本文提出使用基于 BERTScore 评估指标的新型训练目标对神经机器翻译模型进行微调，以克服在训练过程中出现的过拟合偏见问题；作者提出三种生成软预测的方法，可使网络保持端到端的完全可微性，实验表明在四种不同的语言对上，微调目前具有一个强基线模型的 BLEU 分数提高了 0.58pp（3.28%），BERTScore 得分提高了 0.76pp（0.98%）。