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

By Binzong Geng, Fajie Yuan, Qiancheng Xu, Ying Shen, Ruifeng Xu, Min Yang. 2021

42 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Efficiency & Compression, Dialogue & Conversational AI, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hang Su
2. Minlie Huang
3. Jun Zhu
4. Xiaoyan Zhu
5. Liyuan Wang
6. Xingxing Zhang
7. Michael Heck
8. Carel van Niekerk

In Efficiency & Compression

1. Liyuan Wang
2. Jun Zhu
3. Minlie Huang
4. Hang Su
5. Fei Mi
6. Xingxing Zhang

In Dialogue & Conversational AI

1. Minlie Huang
2. Xiaoyan Zhu
3. Qi Zhu
4. Bing Li
5. Fei Mi
6. Jason Aaron Edward Weston

In Meta & Continual Learning

1. Xingxing Zhang
2. Liyuan Wang
3. Hang Su
4. Jun Zhu
5. Michael Heck
6. Carel van Niekerk
7. Nurul Lubis
8. Qi Zhu

Citations in the corpus

• A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “MBPA++ [442], EMAR [465], DnR [396], ARPER [298], Total Recall [253]), generative replay (PAGeR [415], LAMOL [395], ACM [499], NER [434]), parameter allocation (TPEM [131]), modular network (ProgModel [377]), meta-learning (MetaMBPA++ [442], MeLL [422], CML [455]), etc.”
• Dynamic Dialogue Policy for Continual Reinforcement Learning (2022, background): “Geng et al. (2021) proposed a network pruning and expanding strategy for natural language generation.”
• Continual Prompt Tuning for Dialog State Tracking (2022, methodology): “For continual learning in dialog system, variants of general CL methods have been applied (Lee, 2017; Shen et al., 2019; Wu et al., 2019; Mi et al., 2020; Geng et al., 2021).”
• Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue (2022, background): “…specific information to route through the architecture (Mundt et al., 2020), while other studies (Rusu et al., 2016; Aljundi et al., 2017; Zhai et al., 2020; Madotto et al., 2021; Ke et al., 2021; Geng et al., 2021; Zhao et al., 2022b) dynamically grow the architecture in the LL training process.”
• Dynamic Dialogue Policy Transformer for Continual Reinforcement Learning (2022, background): “Other works concentrated on dialogue state tracking (Wu et al., 2019) or natural language generation (Mi et al., 2020; Geng et al., 2021).”