Dual Class Knowledge Propagation Network for Multi-label Few-shot Intent Detection

Feng Zhang, Wei Chen, Fei Ding, Tengjiao Wang


Abstract
Multi-label intent detection aims to assign multiple labels to utterances and attracts increasing attention as a practical task in task-oriented dialogue systems. As dialogue domains change rapidly and new intents emerge fast, the lack of annotated data motivates multi-label few-shot intent detection. However, previous studies are confused by the identical representation of the utterance with multiple labels and overlook the intrinsic intra-class and inter-class interactions. To address these two limitations, we propose a novel dual class knowledge propagation network in this paper. In order to learn well-separated representations for utterances with multiple intents, we first introduce a label-semantic augmentation module incorporating class name information. For better consideration of the inherent intra-class and inter-class relations, an instance-level and a class-level graph neural network are constructed, which not only propagate label information but also propagate feature structure. And we use a simple yet effective method to predict the intent count of each utterance. Extensive experimental results on two multi-label intent datasets have demonstrated that our proposed method outperforms strong baselines by a large margin.
Anthology ID:
2023.acl-long.480
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8605–8618
Language:
URL:
https://aclanthology.org/2023.acl-long.480
DOI:
10.18653/v1/2023.acl-long.480
Bibkey:
Cite (ACL):
Feng Zhang, Wei Chen, Fei Ding, and Tengjiao Wang. 2023. Dual Class Knowledge Propagation Network for Multi-label Few-shot Intent Detection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8605–8618, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Dual Class Knowledge Propagation Network for Multi-label Few-shot Intent Detection (Zhang et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.480.pdf
Video:
 https://aclanthology.org/2023.acl-long.480.mp4