用最优传输优化文档生成的贝叶斯风险解码，提升长文本质量。
Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport
- 引入最优传输计算文档级效用，改进传统贝叶斯风险解码
- 在机器翻译、文本简化等任务中显著优于标准MBR方法
- 适合需要高连贯性长文本生成的研究与应用
文档级文本生成比句子级更困难，因其需理解更长上下文以生成高质量文本。本文研究将最小贝叶斯风险（MBR）解码应用于文档级生成任务。尽管MBR在句子级生成中表现良好，但在文档级效果受限，因多数效用函数针对句子设计。为此，我们提出MBR-OT，利用瓦瑟斯坦距离结合句级效用函数评估文档效用。实验表明，MBR-OT在文档级机器翻译、文本简化及密集图像描述任务中均优于标准MBR。代码已开源：https://github.com/jinnaiyuu/mbr-optimal-transport。
原文摘要 · Abstract (English)
Document-level text generation tasks are known to be more difficult than sentence-level text generation tasks as they require the understanding of longer context to generate high-quality texts. In this paper, we investigate the adaption of Minimum Bayes Risk (MBR) decoding for document-level text generation tasks. MBR decoding makes use of a utility function to estimate the output with the highest expected utility from a set of candidate outputs. Although MBR decoding is shown to be effective in a wide range of sentence-level text generation tasks, its performance on document-level text generation tasks is limited as many of the utility functions are designed for evaluating the utility of sentences. To this end, we propose MBR-OT, a variant of MBR decoding using Wasserstein distance to compute the utility of a document using a sentence-level utility function. The experimental result shows that the performance of MBR-OT outperforms that of the standard MBR in document-level machine translation, text simplification, and dense image captioning tasks. Our code is available at https://github.com/jinnaiyuu/mbr-optimal-transport
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。