Incremental Intent Detection for Medical Domain with Contrast Replay Networks

Guirong Bai, Shizhu He, Kang Liu, Jun Zhao


Abstract
Conventional approaches to medical intent detection require fixed pre-defined intent categories. However, due to the incessant emergence of new medical intents in the real world, such requirement is not practical. Considering that it is computationally expensive to store and re-train the whole data every time new data and intents come in, we propose to incrementally learn emerged intents while avoiding catastrophically forgetting old intents. We first formulate incremental learning for medical intent detection. Then, we employ a memory-based method to handle incremental learning. We further propose to enhance the method with contrast replay networks, which use multilevel distillation and contrast objective to address training data imbalance and medical rare words respectively. Experiments show that the proposed method outperforms the state-of-the-art model by 5.7% and 9.1% of accuracy on two benchmarks respectively.
Anthology ID:
2022.findings-acl.280
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3549–3556
Language:
URL:
https://aclanthology.org/2022.findings-acl.280
DOI:
10.18653/v1/2022.findings-acl.280
Bibkey:
Cite (ACL):
Guirong Bai, Shizhu He, Kang Liu, and Jun Zhao. 2022. Incremental Intent Detection for Medical Domain with Contrast Replay Networks. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3549–3556, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Incremental Intent Detection for Medical Domain with Contrast Replay Networks (Bai et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.280.pdf
Data
KUAKE-QIC