论文标题
提示和速率：一种使用小语言模型的零拍和几个任意文本样式转移的方法
Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models
论文作者
论文摘要
我们提出了一种任意文本样式转移（TST）的方法 - 将文本转换为任何给定样式的任务 - 使通用预培训的语言模型限制。我们的方法（及时及时）基于TST任务的数学表述，将其分解为三个组成部分：文本相似性，目标样式强度和流利度。具体而言，我们的方法首先使用零射击或几次弹药提示，以获取目标样式的一组候选世代，然后根据上面三个组件的组合将这些候选者重新列为这些候选者。从经验上讲，我们的方法使小型的预训练的语言模型能够与最先进的大规模模型相同，同时消耗两个数量级的计算和记忆。最后，我们对模型尺寸和及时设计的影响（例如，及时释义和定界符选择）的效果进行了系统的研究，对七种不同的文本样式传输数据集的样式传输质量。
We propose a method for arbitrary textual style transfer (TST)--the task of transforming a text into any given style--utilizing general-purpose pre-trained language models. Our method, Prompt-and-Rerank, is based on a mathematical formulation of the TST task, decomposing it into three constituent components: textual similarity, target style strength, and fluency. Specifically, our method first uses zero-shot or few-shot prompting to obtain a set of candidate generations in the target style, and then re-ranks these candidates according to a combination of the three components above. Empirically, our method enables small pre-trained language models to perform on par with state-of-the-art large-scale models while consuming two orders of magnitude less compute and memory. Finally, we conduct a systematic investigation of the effect of model size and prompt design (e.g., prompt paraphrasing and delimiter-pair choice) on style transfer quality across seven diverse textual style transfer datasets.
