mbrs:一个用于最小贝叶斯风险解码的库
mbrs: A Library for Minimum Bayes Risk Decoding
AI总结:
mbrs 是一个用于最小贝叶斯风险解码的开源库,可灵活组合多种度量、期望估计和算法变体,并注重速度测量、透明性、可复现性与可扩展性。
摘要:
最小贝叶斯风险(MBR)解码是文本生成任务的一种决策规则,它通过基于效用函数选择高质量输出,而非选择高概率输出,优于使用束搜索的传统最大后验(MAP)解码。通常,它在采样的伪参考下从假设集合中找出最合适的假设。mbrs 是一个 MBR 解码库,可以灵活地组合各种度量、替代期望估计和算法变体。它的设计重点是代码块的速度测量和调用计数、透明性、可复现性和可扩展性,这些对研究人员和开发者至关重要。我们将 mbrs 作为 MIT 许可的开源项目发布,代码可在 GitHub 上获取。
英文摘要:
Minimum Bayes risk (MBR) decoding is a decision rule of text generation tasks that outperforms conventional maximum a posterior (MAP) decoding using beam search by selecting high-quality outputs based on a utility function rather than those with high-probability. Typically, it finds the most suitable hypothesis from the set of hypotheses under the sampled pseudo-references. mbrs is a library of MBR decoding, which can flexibly combine various metrics, alternative expectation estimations, and algorithmic variants. It is designed with a focus on speed measurement and calling count of code blocks, transparency, reproducibility, and extensibility, which are essential for researchers and developers. We published our mbrs as an MIT-licensed open-source project, and the code is available on GitHub. GitHub: https://github.com/naist-nlp/mbrs
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。