Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation

Dingcheng Li, Zheng Chen, Eunah Cho, Jie Hao, Xiaohu Liu, Fan Xing, Chenlei Guo, Yang Liu


Abstract
Seq2seq language generation models that are trained offline with multiple domains in a sequential fashion often suffer from catastrophic forgetting. Lifelong learning has been proposed to handle this problem. However, existing work such as experience replay or elastic weighted consolidation requires incremental memory space. In this work, we propose an innovative framework, RMR_DSEthat leverages a recall optimization mechanism to selectively memorize important parameters of previous tasks via regularization, and uses a domain drift estimation algorithm to compensate the drift between different do-mains in the embedding space. These designs enable the model to be trained on the current task while keep-ing the memory of previous tasks, and avoid much additional data storage. Furthermore, RMR_DSE can be combined with existing lifelong learning approaches. Our experiments on two seq2seq language generation tasks, paraphrase and dialog response generation, show thatRMR_DSE outperforms SOTA models by a considerable margin and reduces forgetting greatly.
Anthology ID:
2022.naacl-main.398
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5441–5454
Language:
URL:
https://aclanthology.org/2022.naacl-main.398
DOI:
10.18653/v1/2022.naacl-main.398
Bibkey:
Cite (ACL):
Dingcheng Li, Zheng Chen, Eunah Cho, Jie Hao, Xiaohu Liu, Fan Xing, Chenlei Guo, and Yang Liu. 2022. Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5441–5454, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation (Li et al., NAACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.naacl-main.398.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2022.naacl-main.398.mp4