Although large language models(LLMs) show amazing capabilities, among various exciting applications discovered for LLMs fall short in other low-resource languages. Besides, most existing methods depend on large-scale dialogue corpora and thus building systems for dialogue generation in a zero-shot scenario remains a considerable challenge. To address this challenge, we propose a novel end-to-end zero-shot dialogue generation model ChatZero based on cross-lingual code-switching method. First, we construct code-switching language and pseudo-target language with placeholders. Then for cross-lingual semantic transfer, we employ unsupervised contrastive learning to minimize the semantics gap of the source language, code-switching language, and pseudo-target language that are mutually positive examples in the high dimensional semantic space. Experiments on the multilingual DailyDialog and DSTC7-AVSD datasets demonstrate that ChatZero can achieve more than 90\% of the original performance under the zero-shot case compared to supervised learning, and achieve state-of-the-art performance compared with other baselines.

本研究解决了在低资源语言中生成对话的挑战，现有方法依赖于大规模对话语料库。通过创新的跨语言代码切换方法，提出了零-shot对话生成模型ChatZero，并通过无监督对比学习来缩小源语言和伪目标语言之间的语义差距。实验结果表明，ChatZero在多语言数据集上表现出色，达到了监督学习的90%以上性能，且在其他基线中取得了最新的性能。 

ChatZero：通过伪目标语言实现零-shot跨语言对话生成