This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective and efficient to simply fine-tune BERT with a small set of labeled utterances from public datasets. Specifically, fine-tuning BERT with roughly 1,000 labeled data yields a pre-trained model -- IntentBERT, which can easily surpass the performance of existing pre-trained models for few-shot intent classification on novel domains with very different semantics. The high effectiveness of IntentBERT confirms the feasibility and practicality of few-shot intent detection, and its high generalization ability across different domains suggests that intent classification tasks may share a similar underlying structure, which can be efficiently learned from a small set of labeled data. The source code can be found at https://github.com/hdzhang-code/IntentBERT.
@article{arxiv.2109.05782,
title = {Effectiveness of Pre-training for Few-shot Intent Classification},
author = {Haode Zhang and Yuwei Zhang and Li-Ming Zhan and Jiaxin Chen and Guangyuan Shi and Albert Y. S. Lam and Xiao-Ming Wu},
journal= {arXiv preprint arXiv:2109.05782},
year = {2024}
}
Comments
Accepted as a short paper in Findings of EMNLP 2021