Dialogue systems for non-English languages have long been under-explored. In
this paper, we take the first step to investigate few-shot cross-lingual
transfer learning (FS-XLT) and multitask learning (MTL) in the context of
open-domain dialogue generation for non-English languages with limited data. We
observed catastrophic forgetting in both FS-XLT and MTL for all 6 languages in
our preliminary experiments. To mitigate the issue, we propose a simple yet
effective prompt learning approach that can preserve the multilinguality of
multilingual pre-trained language model (mPLM) in FS-XLT and MTL by bridging
the gap between pre-training and fine-tuning with Fixed-prompt LM Tuning and
our hand-crafted prompts. Experimental results on all 6 languages in terms of
both automatic and human evaluations demonstrate the effectiveness of our
approach. Our code is available at this https URL

本文探讨了如何在有限数据的情况下，使用少量样本跨语言迁移学习和多任务学习来进行开放域对话生成，同时发现了这两种方法在实验中的灾难性遗忘问题，并提出了一种简单有效的提示学习方法，以应对这一问题。实验结果表明，该方法在六种语言中均表现出了较好的效果。

跨语言转移开放域对话生成中减轻灾难性遗忘的提示学习

Prompt Learning to Mitigate Catastrophic Forgetting in Cross-lingual  Transfer for Open-domain Dialogue Generation

The current state-of-the-art for few-shot cross-lingual transfer learning
first trains on abundant labeled data in the source language and then
fine-tunes with a few examples on the target language, termed target-adapting.
Though this has been demonstrated to work on a variety of tasks, in this paper
we show some deficiencies of this approach and propose a one-step mixed
training method that trains on both source and target data with
\textit{stochastic gradient surgery}, a novel gradient-level optimization.
Unlike the previous studies that focus on one language at a time when
target-adapting, we use one model to handle all target languages simultaneously
to avoid excessively language-specific models. Moreover, we discuss the
unreality of utilizing large target development sets for model selection in
previous literature. We further show that our method is both development-free
for target languages, and is also able to escape from overfitting issues. We
conduct a large-scale experiment on 4 diverse NLP tasks across up to 48
languages. Our proposed method achieves state-of-the-art performance on all
tasks and outperforms target-adapting by a large margin, especially for
languages that are linguistically distant from the source language, e.g., 7.36%
F1 absolute gain on average for the NER task, up to 17.60% on Punjabi.

本文提出一种混合训练方法，使用随机梯度削减策略对源语言和目标语言的数据进行联合学习，避免了过多的针对特定语言的模型，并证明了该方法在跨多种语言下比传统的 few-shot cross-lingual transfer learning 方法表现更好且不需要选择目标语言的开发集。