Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction
Caiyuan Chu, Ya Li, Yifan Liu, Jia-Chen Gu, Quan Liu, Yongxin Ge, Guoping Hu
Abstract
Intent recognition is critical for task-oriented dialogue systems. However, for emerging domains and new services, it is difficult to accurately identify the key intent of a conversation due to time-consuming data annotation and comparatively poor model transferability. Therefore, the automatic induction of dialogue intention is very important for intelligent dialogue systems. This paper presents our solution to Track 2 of Intent Induction from Conversations for Task-Oriented Dialogue at the Eleventh Dialogue System Technology Challenge (DSTC11). The essence of intention clustering lies in distinguishing the representation of different dialogue utterances. The key to automatic intention induction is that, for any given set of new data, the sentence representation obtained by the model can be well distinguished from different labels. Therefore, we propose a multi-stage coarse-to-fine contrastive learning model training scheme including unsupervised contrastive learning pre-training, supervised contrastive learning pre-training, and fine-tuning with joint contrastive learning and clustering to obtain a better dialogue utterance representation model for the clustering task. In the released DSTC11 Track 2 evaluation results, our proposed system ranked first on both of the two subtasks of this Track.- Anthology ID:
- 2023.dstc-1.5
- Volume:
- Proceedings of The Eleventh Dialog System Technology Challenge
- Month:
- September
- Year:
- 2023
- Address:
- Prague, Czech Republic
- Editors:
- Yun-Nung Chen, Paul Crook, Michel Galley, Sarik Ghazarian, Chulaka Gunasekara, Raghav Gupta, Behnam Hedayatnia, Satwik Kottur, Seungwhan Moon, Chen Zhang
- Venues:
- DSTC | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 31–39
- Language:
- URL:
- https://aclanthology.org/2023.dstc-1.5
- DOI:
- Cite (ACL):
- Caiyuan Chu, Ya Li, Yifan Liu, Jia-Chen Gu, Quan Liu, Yongxin Ge, and Guoping Hu. 2023. Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction. In Proceedings of The Eleventh Dialog System Technology Challenge, pages 31–39, Prague, Czech Republic. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction (Chu et al., DSTC-WS 2023)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2023.dstc-1.5.pdf