Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks

Zixuan Ke, Hu Xu, Bing Liu


Abstract
This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware of any CL work on ASC. A CL system that incrementally learns a sequence of ASC tasks should address the following two issues: (1) transfer knowledge learned from previous tasks to the new task to help it learn a better model, and (2) maintain the performance of the models for previous tasks so that they are not forgotten. This paper proposes a novel capsule network based model called B-CL to address these issues. B-CL markedly improves the ASC performance on both the new task and the old tasks via forward and backward knowledge transfer. The effectiveness of B-CL is demonstrated through extensive experiments.
Anthology ID:
2021.naacl-main.378
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:
4746–4755
Language:
URL:
https://aclanthology.org/2021.naacl-main.378
DOI:
10.18653/v1/2021.naacl-main.378
Bibkey:
Cite (ACL):
Zixuan Ke, Hu Xu, and Bing Liu. 2021. Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4746–4755, Online. Association for Computational Linguistics.
Cite (Informal):
Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks (Ke et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.378.pdf
Video:
 https://aclanthology.org/2021.naacl-main.378.mp4
Code
 zixuanke/pycontinual
Data
ASC (TIL, 19 tasks)20Newsgroup (10 tasks)DSC (10 tasks)