Exploring Zero and Few-shot Techniques for Intent Classification
Soham Parikh, Mitul Tiwari, Prashil Tumbade, Quaizar Vohra · 2023
Conversational NLU providers often need to scale to thousands of intent-classification models where new customers often face the coldstart 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 finetuning using T-few recipe (Liu et al., 2022) on Flan-T5 (Chung 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 is also very competitive.