Minimum Bayes risk (MBR) decoding is a decision rule of text generation, which selects the hypothesis that maximizes the expected utility and robustly generates higher-quality texts than maximum a posteriori (MAP) decoding. However, it depends on sample texts drawn from the text generation model; thus, it is difficult to find a hypothesis that correctly captures the knowledge or information of out-of-domain. To tackle this issue, we propose case-based decision-theoretic (CBDT) decoding, another method to estimate the expected utility using examples of domain data. CBDT decoding not only generates higher-quality texts than MAP decoding, but also the combination of MBR and CBDT decoding outperformed MBR decoding in seven domain De--En and Ja$\leftrightarrow$En translation tasks and image captioning tasks on MSCOCO and nocaps datasets.

翻译：最小贝叶斯风险（MBR）解码是一种文本生成的决策规则，它选择能够最大化期望效用的假设，相比最大后验概率（MAP）解码，能够更稳健地生成更高质量的文本。然而，该方法依赖于从文本生成模型中采样的文本，因此难以找到能够准确捕捉领域外知识或信息的假设。为解决这一问题，我们提出了基于案例的决策理论（CBDT）解码，这是一种利用领域数据示例来估计期望效用的新方法。CBDT解码不仅比MAP解码生成更高质量的文本，而且MBR与CBDT解码的组合在七个领域（德-英和日$\leftrightarrow$英翻译任务）以及MSCOCO和nocaps数据集上的图像描述生成任务中，其性能均优于单独的MBR解码。