Abstract | ||
---|---|---|
Identifying intentions from users can help improve the response quality of task-oriented dialogue systems. How to use only limited labeled in-domain (ID) examples for zero-shot unknown intent detection and few-shot ID classification is a more challenging task in spoken language understanding. Existing related methods heavily rely upon the multi-domain datasets containing large-scale independent source domains for meta-training. In this paper, we propose a universal In-scope Prototypical Networks for low-resource intent detection to be general to dialogue meta-train datasets lacking widely-varying domains, which focuses on the scope of episodic intent classes to construct meta-task dynamically. Also, we introduce loss with margin principle to better distinguish samples. Experiments on two benchmark datasets show that our model consistently outperforms other baselines on zero-shot unknown intent detection without deteriorating the competitive performance on few-shot ID classification. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICASSP39728.2021.9414548 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
Low-resource, unknown intent, scope, prototypical networks, loss with margin principle | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hongzhan Lin | 1 | 0 | 1.01 |
Yuanmeng Yan | 2 | 0 | 4.06 |
Guang Chen | 3 | 30 | 4.68 |