Exploring Zero and Few-shot Techniques for Intent Classification. (arXiv:2305.07157v1 [cs.CL])

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 …

arxiv classification conversational customers face low nlu paper scale scaling space storage