This paper explores Minimum Bayes Risk (MBR) decoding for self-improvement in machine translation (MT), particularly for domain adaptation and low-resource languages. We implement the self-improvement process by fine-tuning the model on its MBR-decoded forward translations. By employing COMET as the MBR utility metric, we aim to achieve the reranking of translations that better aligns with human preferences. The paper explores the iterative application of this approach and the potential need for language-specific MBR utility metrics. The results demonstrate significant enhancements in translation quality for all examined language pairs, including successful application to domain-adapted models and generalisation to low-resource settings. This highlights the potential of COMET-guided MBR for efficient MT self-improvement in various scenarios.

翻译：本文研究了最小贝叶斯风险（MBR）解码在机器翻译（MT）自我改进中的应用，尤其针对领域自适应和低资源语言场景。我们通过将模型在其MBR解码前向翻译结果上进行微调，实现了自我改进流程。采用COMET作为MBR效用度量指标，旨在实现更符合人类偏好的翻译重排序。本文探讨了该方法的迭代应用以及语言特定MBR效用度量的潜在需求。实验结果表明，所有受检语言对的翻译质量均得到显著提升，包括成功应用于领域自适应模型及泛化至低资源场景。这凸显了COMET引导的MBR在不同场景下实现高效MT自我改进的潜力。