Abstract
This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each task is from a different domain or product. The DIL setting is particularly suited to ASC because in testing the system needs not know the task/domain to which the test data belongs. To our knowledge, this setting has not been studied before for ASC. This paper proposes a novel model called CLASSIC. The key novelty is a contrastive continual learning method that enables both knowledge transfer across tasks and knowledge distillation from old tasks to the new task, which eliminates the need for task ids in testing. Experimental results show the high effectiveness of CLASSIC.- Anthology ID:
- 2021.emnlp-main.550
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6871–6883
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.550
- DOI:
- 10.18653/v1/2021.emnlp-main.550
- Cite (ACL):
- Zixuan Ke, Bing Liu, Hu Xu, and Lei Shu. 2021. CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6871–6883, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks (Ke et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2021.emnlp-main.550.pdf
- Code
- zixuanke/pycontinual