Exploring Zero and Few-shot Techniques for Intent Classification

Soham Parikh, Mitul Tiwari, Prashil Tumbade, Quaizar Vohra


Abstract
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 on Flan-T5 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.
Anthology ID:
2023.acl-industry.71
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
Month:
July
Year:
2023
Address:
Toronto, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
744–751
Language:
URL:
https://aclanthology.org/2023.acl-industry.71
DOI:
Bibkey:
Cite (ACL):
Soham Parikh, Mitul Tiwari, Prashil Tumbade, and Quaizar Vohra. 2023. Exploring Zero and Few-shot Techniques for Intent Classification. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 744–751, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Exploring Zero and Few-shot Techniques for Intent Classification (Parikh et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/2023.acl-industry.71.pdf