Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding
Ting Hua, Yilin Shen, Changsheng Zhao, Yen-Chang Hsu, Hongxia Jin
Abstract
Domain classification is the fundamental task in natural language understanding (NLU), which often requires fast accommodation to new emerging domains. This constraint makes it impossible to retrain all previous domains, even if they are accessible to the new model. Most existing continual learning approaches suffer from low accuracy and performance fluctuation, especially when the distributions of old and new data are significantly different. In fact, the key real-world problem is not the absence of old data, but the inefficiency to retrain the model with the whole old dataset. Is it potential to utilize some old data to yield high accuracy and maintain stable performance, while at the same time, without introducing extra hyperparameters? In this paper, we proposed a hyperparameter-free continual learning model for text data that can stably produce high performance under various environments. Specifically, we utilize Fisher information to select exemplars that can “record” key information of the original model. Also, a novel scheme called dynamical weight consolidation is proposed to enable hyperparameter-free learning during the retrain process. Extensive experiments demonstrate baselines provide fluctuated performance which makes them useless in practice. On the contrary, our proposed model significantly and consistently outperforms the best state-of-the-art method by up to 20% in average accuracy, and each of its component contributes effectively to overall performance.- Anthology ID:
- 2021.naacl-main.212
- 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:
- 2669–2678
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.212
- DOI:
- 10.18653/v1/2021.naacl-main.212
- Cite (ACL):
- Ting Hua, Yilin Shen, Changsheng Zhao, Yen-Chang Hsu, and Hongxia Jin. 2021. Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2669–2678, Online. Association for Computational Linguistics.
- Cite (Informal):
- Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding (Hua et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2021.naacl-main.212.pdf