KNN-Contrastive Learning for Out-of-Domain Intent Classification

Yunhua Zhou, Peiju Liu, Xipeng Qiu


Abstract
The Out-of-Domain (OOD) intent classification is a basic and challenging task for dialogue systems. Previous methods commonly restrict the region (in feature space) of In-domain (IND) intent features to be compact or simply-connected implicitly, which assumes no OOD intents reside, to learn discriminative semantic features. Then the distribution of the IND intent features is often assumed to obey a hypothetical distribution (Gaussian mostly) and samples outside this distribution are regarded as OOD samples. In this paper, we start from the nature of OOD intent classification and explore its optimization objective. We further propose a simple yet effective method, named KNN-contrastive learning. Our approach utilizes k-nearest neighbors (KNN) of IND intents to learn discriminative semantic features that are more conducive to OOD detection. Notably, the density-based novelty detection algorithm is so well-grounded in the essence of our method that it is reasonable to use it as the OOD detection algorithm without making any requirements for the feature distribution. Extensive experiments on four public datasets show that our approach can not only enhance the OOD detection performance substantially but also improve the IND intent classification while requiring no restrictions on feature distribution.
Anthology ID:
2022.acl-long.352
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5129–5141
Language:
URL:
https://aclanthology.org/2022.acl-long.352
DOI:
10.18653/v1/2022.acl-long.352
Bibkey:
Cite (ACL):
Yunhua Zhou, Peiju Liu, and Xipeng Qiu. 2022. KNN-Contrastive Learning for Out-of-Domain Intent Classification. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5129–5141, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
KNN-Contrastive Learning for Out-of-Domain Intent Classification (Zhou et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.352.pdf