Abstract | ||
---|---|---|
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 non-parametric 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. Data and code are available at https://github.com/AtmaHou/FewShotMultiLabel. |
Year | Venue | DocType |
---|---|---|
2021 | THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Conference |
Volume | ISSN | Citations |
35 | 2159-5399 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yutai Hou | 1 | 3 | 3.43 |
Yongkui Lai | 2 | 0 | 1.01 |
Yushan Wu | 3 | 0 | 0.68 |
Wanxiang Che | 4 | 711 | 66.39 |
Ting Liu | 5 | 2735 | 232.31 |