Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification

Guangfeng Yan, Lu Fan, Qimai Li, Han Liu, Xiaotong Zhang, Xiao-Ming Wu, Albert Y.S. Lam


Abstract
User intent classification plays a vital role in dialogue systems. Since user intent may frequently change over time in many realistic scenarios, unknown (new) intent detection has become an essential problem, where the study has just begun. This paper proposes a semantic-enhanced Gaussian mixture model (SEG) for unknown intent detection. In particular, we model utterance embeddings with a Gaussian mixture distribution and inject dynamic class semantic information into Gaussian means, which enables learning more class-concentrated embeddings that help to facilitate downstream outlier detection. Coupled with a density-based outlier detection algorithm, SEG achieves competitive results on three real task-oriented dialogue datasets in two languages for unknown intent detection. On top of that, we propose to integrate SEG as an unknown intent identifier into existing generalized zero-shot intent classification models to improve their performance. A case study on a state-of-the-art method, ReCapsNet, shows that SEG can push the classification performance to a significantly higher level.
Anthology ID:
2020.acl-main.99
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1050–1060
Language:
URL:
https://aclanthology.org/2020.acl-main.99
DOI:
10.18653/v1/2020.acl-main.99
Bibkey:
Cite (ACL):
Guangfeng Yan, Lu Fan, Qimai Li, Han Liu, Xiaotong Zhang, Xiao-Ming Wu, and Albert Y.S. Lam. 2020. Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1050–1060, Online. Association for Computational Linguistics.
Cite (Informal):
Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification (Yan et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.99.pdf
Video:
 http://slideslive.com/38929387
Code
 fanolabs/0shot-classification