Prompting shows promising results in few-shot scenarios. However, its strength for multilingual/cross-lingual problems has not been fully exploited. Zhao and Sch\"utze (2021) made initial explorations in this direction by presenting that cross-lingual prompting outperforms cross-lingual finetuning. In this paper, we conduct an empirical exploration on the effect of each component in cross-lingual prompting and derive language-agnostic Universal Prompting, which helps alleviate the discrepancies between source-language training and target-language inference. Based on this, we propose DPA, a dual prompt augmentation framework, aiming at relieving the data scarcity issue in few-shot cross-lingual prompting. Notably, for XNLI, our method achieves 46.54% with only 16 English training examples per class, significantly better than 34.99% of finetuning. Our code is available at https://github.com/DAMO-NLP-SG/DPA.

翻译：提示学习在少样本场景中展现出令人鼓舞的效果。然而，其在多语言/跨语言问题中的优势尚未得到充分挖掘。Zhao与Schütze（2021）通过论证跨语言提示学习优于跨语言微调，在该方向进行了初步探索。本文对各组件在跨语言提示中的作用开展了实证研究，并推导出语言无关的通用提示方法，有助于缓解源语言训练与目标语言推理之间的差异。基于此，我们提出DPA——一种双重提示增强框架，旨在缓解少样本跨语言提示中的数据稀缺问题。值得注意的是，在XNLI数据集上，我们的方法仅凭每类16个英文训练样本即达到46.54%的准确率，显著优于微调方法的34.99%。相关代码已开源至https://github.com/DAMO-NLP-SG/DPA。