Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery

Yutao Mou, Xiaoshuai Song, Keqing He, Chen Zeng, Pei Wang, Jingang Wang, Yunsen Xian, Weiran Xu


Abstract
Generalized intent discovery aims to extend a closed-set in-domain intent classifier to an open-world intent set including in-domain and out-of-domain intents. The key challenges lie in pseudo label disambiguation and representation learning. Previous methods suffer from a coupling of pseudo label disambiguation and representation learning, that is, the reliability of pseudo labels relies on representation learning, and representation learning is restricted by pseudo labels in turn. In this paper, we propose a decoupled prototype learning framework (DPL) to decouple pseudo label disambiguation and representation learning. Specifically, we firstly introduce prototypical contrastive representation learning (PCL) to get discriminative representations. And then we adopt a prototype-based label disambiguation method (PLD) to obtain pseudo labels. We theoretically prove that PCL and PLD work in a collaborative fashion and facilitate pseudo label disambiguation. Experiments and analysis on three benchmark datasets show the effectiveness of our method.
Anthology ID:
2023.acl-long.538
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:
9661–9675
Language:
URL:
https://aclanthology.org/2023.acl-long.538
DOI:
10.18653/v1/2023.acl-long.538
Bibkey:
Cite (ACL):
Yutao Mou, Xiaoshuai Song, Keqing He, Chen Zeng, Pei Wang, Jingang Wang, Yunsen Xian, and Weiran Xu. 2023. Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9661–9675, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery (Mou et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.538.pdf
Video:
 https://aclanthology.org/2023.acl-long.538.mp4