Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based ``hard prompts'' to continuous ``soft prompts'', which employ learnable vectors as pseudo prompt tokens and achieve better performance. Though showing promising prospects, these soft-prompting methods are observed to rely heavily on good initialization to take effect. Unfortunately, obtaining a perfect initialization for soft prompts requires understanding of inner language models working and elaborate design, which is no easy task and has to restart from scratch for each new task. To remedy this, we propose a generalized soft prompting method called MetaPrompting, which adopts the well-recognized model-agnostic meta-learning algorithm to automatically find better prompt initialization that facilitates fast adaptation to new prompting tasks.Extensive experiments show MetaPrompting tackles soft prompt initialization problem and brings significant improvement on four different datasets (over 6 points improvement in accuracy for 1-shot setting), achieving new state-of-the-art performance.

翻译：提示方法被认为是少样本自然语言处理领域的关键进展之一。近期关于提示的研究正从基于离散标记的“硬提示”转向连续的“软提示”，后者采用可学习向量作为伪提示标记，并取得了更优的性能。尽管展现出光明前景，但这些软提示方法被观察到严重依赖良好的初始化才能发挥作用。不幸的是，为软提示获得完美的初始化需要深入理解内部语言模型的工作机制并进行精细设计，这并非易事，且每个新任务都需从头开始。为解决这一问题，我们提出一种名为MetaPrompting的泛化软提示方法，该方法采用广受认可的模型无关元学习算法，自动寻找到更好的提示初始化，从而促进快速适应新的提示任务。大量实验表明，MetaPrompting解决了软提示初始化问题，并在四个不同数据集上带来了显著提升（在1-shot设置下准确率提升超过6个百分点），达到了新的最优性能。