Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking

Binzong Geng, Fajie Yuan, Qiancheng Xu, Ying Shen, Ruifeng Xu, Min Yang


Abstract
This ability to learn consecutive tasks without forgetting how to perform previously trained problems is essential for developing an online dialogue system. This paper proposes an effective continual learning method for the task-oriented dialogue system with iterative network pruning, expanding, and masking (TPEM), which preserves performance on previously encountered tasks while accelerating learning progress on subsequent tasks. Specifically, TPEM (i) leverages network pruning to keep the knowledge for old tasks, (ii) adopts network expanding to create free weights for new tasks, and (iii) introduces task-specific network masking to alleviate the negative impact of fixed weights of old tasks on new tasks. We conduct extensive experiments on seven different tasks from three benchmark datasets and show empirically that TPEM leads to significantly improved results over the strong competitors.
Anthology ID:
2021.acl-short.66
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
517–523
Language:
URL:
https://aclanthology.org/2021.acl-short.66
DOI:
10.18653/v1/2021.acl-short.66
Bibkey:
Cite (ACL):
Binzong Geng, Fajie Yuan, Qiancheng Xu, Ying Shen, Ruifeng Xu, and Min Yang. 2021. Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 517–523, Online. Association for Computational Linguistics.
Cite (Informal):
Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking (Geng et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.66.pdf
Video:
 https://aclanthology.org/2021.acl-short.66.mp4
Code
 siat-nlp/TPEM