Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue

Yingxiu Zhao, Yinhe Zheng, Zhiliang Tian, Chang Gao, Jian Sun, Nevin L. Zhang


Abstract
Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems. To address the catastrophic forgetting issue of LL, generative replay methods are widely employed to consolidate past knowledge with generated pseudo samples. However, most existing generative replay methods use only a single task-specific token to control their models. This scheme is usually not strong enough to constrain the generative model due to insufficient information involved. In this paper, we propose a novel method, prompt conditioned VAE for lifelong learning (PCLL), to enhance generative replay by incorporating tasks’ statistics. PCLL captures task-specific distributions with a conditional variational autoencoder, conditioned on natural language prompts to guide the pseudo-sample generation. Moreover, it leverages a distillation process to further consolidate past knowledge by alleviating the noise in pseudo samples. Experiments on natural language understanding tasks of ToD systems demonstrate that PCLL significantly outperforms competitive baselines in building lifelong learning models.
Anthology ID:
2022.emnlp-main.766
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11153–11169
Language:
URL:
https://aclanthology.org/2022.emnlp-main.766
DOI:
10.18653/v1/2022.emnlp-main.766
Bibkey:
Cite (ACL):
Yingxiu Zhao, Yinhe Zheng, Zhiliang Tian, Chang Gao, Jian Sun, and Nevin L. Zhang. 2022. Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11153–11169, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue (Zhao et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.766.pdf
Dataset:
 2022.emnlp-main.766.dataset.zip
Software:
 2022.emnlp-main.766.software.zip