Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning
Jianguo Zhang, Trung Bui, Seunghyun Yoon, Xiang Chen, Zhiwei Liu, Congying Xia, Quan Hung Tran, Walter Chang, Philip Yu
Abstract
In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-shot intent detection schema via contrastive pre-training and fine-tuning. Specifically, we first conduct self-supervised contrastive pre-training on collected intent datasets, which implicitly learns to discriminate semantically similar utterances without using any labels. We then perform few-shot intent detection together with supervised contrastive learning, which explicitly pulls utterances from the same intent closer and pushes utterances across different intents farther. Experimental results show that our proposed method achieves state-of-the-art performance on three challenging intent detection datasets under 5-shot and 10-shot settings.- Anthology ID:
- 2021.emnlp-main.144
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1906–1912
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.144
- DOI:
- 10.18653/v1/2021.emnlp-main.144
- Cite (ACL):
- Jianguo Zhang, Trung Bui, Seunghyun Yoon, Xiang Chen, Zhiwei Liu, Congying Xia, Quan Hung Tran, Walter Chang, and Philip Yu. 2021. Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1906–1912, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning (Zhang et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2021.emnlp-main.144.pdf
- Code
- jianguoz/Few-Shot-Intent-Detection + additional community code
- Data
- BANKING77, HWU64