Based on multilingual pre-trained models, cross-lingual transfer with prompt learning has shown promising effectiveness, where soft prompt learned in a source language is transferred to target languages for downstream tasks, particularly in the low-resource scenario. To efficiently transfer soft prompt, we propose a novel framework, Multilingual Prompt Translator (MPT), where a multilingual prompt translator is introduced to properly process crucial knowledge embedded in prompt by changing language knowledge while retaining task knowledge. Concretely, we first train prompt in source language and employ translator to translate it into target prompt. Besides, we extend an external corpus as auxiliary data, on which an alignment task for predicted answer probability is designed to convert language knowledge, thereby equipping target prompt with multilingual knowledge. In few-shot settings on XNLI, MPT demonstrates superiority over baselines by remarkable improvements. MPT is more prominent compared with vanilla prompting when transferring to languages quite distinct from source language.

翻译：基于多语言预训练模型，结合提示学习的跨语言迁移在低资源场景下展现出显著效果，其中在源语言中学习的软提示可迁移至目标语言以完成下游任务。为高效实现软提示的迁移，本文提出一种新颖框架——多语言提示翻译器（Multilingual Prompt Translator, MPT），该框架通过引入多语言提示翻译器，在保留任务知识的同时转换语言知识，从而恰当处理提示中嵌入的关键知识。具体而言，我们首先在源语言中训练提示，并利用翻译器将其转换为目标提示。此外，我们扩展外部语料作为辅助数据，并针对预测答案概率设计对齐任务以转换语言知识，从而使目标提示具备多语言知识。在XNLI数据集的小样本设置下，MPT相较于基线方法展现出显著优势。当迁移至与源语言差异较大的语言时，MPT相比原始提示方法表现更为突出。