Conversational NLU providers often need to scale to thousands of intent-classification models where new customers often face the cold-start problem. Scaling to so many customers puts a constraint on storage space as well. In this paper, we explore four different zero and few-shot intent classification approaches with this low-resource constraint: 1) domain adaptation, 2) data augmentation, 3) zero-shot intent classification using descriptions large language models (LLMs), and 4) parameter-efficient fine-tuning of instruction-finetuned language models. Our results show that all these approaches are effective to different degrees in low-resource settings. Parameter-efficient fine-tuning using T-few recipe (Liu et al., 2022) on Flan-T5 (Chang et al., 2022) yields the best performance even with just one sample per intent. We also show that the zero-shot method of prompting LLMs using intent descriptions

翻译：对话式自然语言理解服务提供商通常需要扩展到数千个意图分类模型，而新客户常面临冷启动问题。扩展到如此多的客户也对存储空间构成了限制。本文在低资源约束下探索了四种不同的零样本与少样本意图分类方法：1）领域自适应；2）数据增强；3）使用大语言模型描述进行零样本意图分类；4）基于指令微调语言模型的参数高效微调。结果表明，这些方法在低资源场景下均具有不同程度的有效性。采用T-few配方对Flan-T5进行参数高效微调，即使每个意图仅有一个样本也能获得最佳性能。我们还证明，通过意图描述提示大语言模型的零样本方法（Lester等人，2021；Brown等人，2020）虽然性能略逊，但在不进行任何训练的情况下提供了实用的基线方案。