Abstract
Emerging intents may have zero or a few labeled samples in realistic dialog systems. Therefore, models need to be capable of performing both zero-shot and few-shot intent detection. However, existing zero-shot intent detection models do not generalize well to few-shot settings and vice versa. To this end, we explore a novel and realistic setting, namely, any-shot intent detection. Based on this new paradigm, we propose Episode-based Prompt Learning (EPL) framework. The framework first reformulates the intent detection task as a sentence-pair classification task using prompt templates and unifies the different settings. Then, it introduces two training mechanisms, which alleviate the impact of different prompt templates on performance and simulate any-shot settings in the training phase, effectively improving the model’s performance. Experimental results on four datasets show that EPL outperforms strong baselines by a large margin on zero-shot and any-shot intent detection and achieves competitive results on few-shot intent detection.
P. Sun and D. Song—Equal contribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Zero-shot intent detection is a setup in which a model can learn to detect intents that it hasn’t explicitly seen before in training [21].
- 2.
Few-shot intent detection is a setup in which a model can learn to detect intents that only a few annotated examples are available [22].
- 3.
Episodic training mechanism attempts to simulate a realistic setting by generating a small set of artificial tasks from a larger set of training tasks for training and proceeds similarly for testing.
References
Bhathiya, H.S., Thayasivam, U.: Meta learning for few-shot joint intent detection and slot-filling. In: ICMLT, pp. 86–92 (2020)
Casanueva, I., Temčinas, T., Gerz, D., Henderson, M., Vulić, I.: Efficient intent detection with dual sentence encoders. In: NLP4ConvAI, pp. 38–45 (2020)
Celikyilmaz, A., Hakkani-Tur, D., Tur, G., Fidler, A., Hillard, D.: Exploiting distance based similarity in topic models for user intent detection. In: ASRU, pp. 425–430 (2011)
Chen, J., Zhang, R., Mao, Y., Xue, J.: ContrastNet: a contrastive learning framework for few-shot text classification. In: AAAI, pp. 10492–10500 (2022)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607 (2020)
Coucke, A., et al.: Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. arXiv preprint arXiv:1805.10190 (2018)
Dopierre, T., Gravier, C., Logerais, W.: ProtAugment: intent detection meta-learning through unsupervised diverse paraphrasing. In: ACL/IJCNLP (2021)
Gururangan, S., et al.: Don’t stop pretraining: adapt language models to domains and tasks. In: ACL, pp. 8342–8360 (2020)
Hu, S., Ding, N., Wang, H., Liu, Z., Li, J.Z., Sun, M.: Knowledgeable prompt-tuning: incorporating knowledge into prompt verbalizer for text classification. ArXiv abs/2108.02035 (2021)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Larson, S., et al.: An evaluation dataset for intent classification and out-of-scope prediction. In: EMNLP-IJCNLP, pp. 1311–1316 (2019)
Li, J.Y., Zhang, J.: Semi-supervised meta-learning for cross-domain few-shot intent classification. In: MetaNLP (2021)
Liu, F., Lin, H., Han, X., Cao, B., Sun, L.: Pre-training to match for unified low-shot relation extraction. arXiv preprint arXiv:2203.12274 (2022)
Liu, X., Eshghi, A., Swietojanski, P., Rieser, V.: Benchmarking natural language understanding services for building conversational agents. In: IWSDS (2019)
Malik, V., Kumar, A., Vepa, J.: Exploring the limits of natural language inference based setup for few-shot intent detection. ArXiv abs/2112.07434 (2021)
Qin, L., Liu, T., Che, W., Kang, B., Zhao, S., Liu, T.: A co-interactive transformer for joint slot filling and intent detection. In: ICASSP, pp. 8193–8197 (2021)
Si, Q., Liu, Y., Fu, P., Lin, Z., Li, J., Wang, W.: Learning class-transductive intent representations for zero-shot intent detection. In: IJCAI (2021)
Sun, Y., Zheng, Y., Hao, C., Qiu, H.: NSP-BERT: a prompt-based zero-shot learner through an original pre-training task-next sentence prediction. ArXiv abs/2109.03564 (2021)
Vinyals, O., Blundell, C., Lillicrap, T.P., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: NIPS (2016)
Wang, J., Wei, K., Radfar, M., Zhang, W., Chung, C.: Encoding syntactic knowledge in transformer encoder for intent detection and slot filling. In: AAAI, vol. 35, pp. 13943–13951 (2021)
Xia, C., Zhang, C., Yan, X., Chang, Y., Philip, S.Y.: Zero-shot user intent detection via capsule neural networks. In: EMNLP, pp. 3090–3099 (2018)
Xu, W., Zhou, P., You, C., Zou, Y.: Semantic transportation prototypical network for few-shot intent detection. In: Interspeech, pp. 251–255 (2021)
Zhang, H., et al.: Effectiveness of pre-training for few-shot intent classification. In: EMNLP, pp. 1114–1120 (2021)
Acknowledgements
The authors would like to thank the anonymous reviewers for their helpful comments. This research is supported by the National Natural Science Foundation of China (No. 61936012, 62206126 and 61976114).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, P., Song, D., Ouyang, Y., Wu, Z., Dai, X. (2023). Episode-Based Prompt Learning for Any-Shot Intent Detection. In: Liu, F., Duan, N., Xu, Q., Hong, Y. (eds) Natural Language Processing and Chinese Computing. NLPCC 2023. Lecture Notes in Computer Science(), vol 14302. Springer, Cham. https://doi.org/10.1007/978-3-031-44693-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-44693-1_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44692-4
Online ISBN: 978-3-031-44693-1
eBook Packages: Computer ScienceComputer Science (R0)
