Adversarial Self-Supervised Learning for Out-of-Domain Detection

Zhiyuan Zeng, Keqing He, Yuanmeng Yan, Hong Xu, Weiran Xu


Abstract
Detecting out-of-domain (OOD) intents is crucial for the deployed task-oriented dialogue system. Previous unsupervised OOD detection methods only extract discriminative features of different in-domain intents while supervised counterparts can directly distinguish OOD and in-domain intents but require extensive labeled OOD data. To combine the benefits of both types, we propose a self-supervised contrastive learning framework to model discriminative semantic features of both in-domain intents and OOD intents from unlabeled data. Besides, we introduce an adversarial augmentation neural module to improve the efficiency and robustness of contrastive learning. Experiments on two public benchmark datasets show that our method can consistently outperform the baselines with a statistically significant margin.
Anthology ID:
2021.naacl-main.447
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5631–5639
Language:
URL:
https://aclanthology.org/2021.naacl-main.447
DOI:
10.18653/v1/2021.naacl-main.447
Bibkey:
Cite (ACL):
Zhiyuan Zeng, Keqing He, Yuanmeng Yan, Hong Xu, and Weiran Xu. 2021. Adversarial Self-Supervised Learning for Out-of-Domain Detection. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5631–5639, Online. Association for Computational Linguistics.
Cite (Informal):
Adversarial Self-Supervised Learning for Out-of-Domain Detection (Zeng et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.447.pdf
Video:
 https://aclanthology.org/2021.naacl-main.447.mp4
Code
 parzival27/adversarial-self-supervised-out-of-domain-detection
Data
CLINC150