Case-Based Decision-Theoretic Decoding with Quality Memories
This addresses a bottleneck in text generation for out-of-domain scenarios, offering an incremental improvement over existing methods.
The paper tackles the problem of MBR decoding's reliance on in-domain samples by proposing CBDT decoding, which uses domain examples to estimate utility, resulting in improved performance over MAP decoding and combined MBR-CBDT outperforming MBR alone in translation and captioning tasks across seven domains.
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.