In this paper, we study the few-shot multi-label classification for user intent detection. For multi-label intent detection, state-of-the-art work estimates label-instance relevance scores and uses a threshold to select multiple associated intent labels. To determine appropriate thresholds with only a few examples, we first learn universal thresholding experience on data-rich domains, and then adapt the thresholds to certain few-shot domains with a calibration based on nonparametric learning. For better calculation of label-instance relevance score, we introduce label name embedding as anchor points in representation space, which refines representations of different classes to be well-separated from each other. Experiments on two datasets show that the proposed model significantly outperforms strong baselines in both one-shot and five-shot settings.
@article{arxiv.2010.05256,
title = {Few-shot Learning for Multi-label Intent Detection},
author = {Yutai Hou and Yongkui Lai and Yushan Wu and Wanxiang Che and Ting Liu},
journal= {arXiv preprint arXiv:2010.05256},
year = {2020}
}