Continual Prompt Tuning for Dialog State Tracking

By Qi Zhu, Bing Li, Fei Mi, Xiaoyan Zhu, Minlie Huang. 2022

69 citations recorded by the source corpus.

A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle. However, continually training a model often leads to a well-known catastrophic forgetting issue. In this paper, we present Continual Prompt Tuning, a parameter-efficient framework that not only avoids forgetting but also enables knowledge transfer between tasks. To avoid forgetting, we only learn and store a few prompt tokens’ embeddings for each task while freezing the backbone pre-trained model. To achieve bi-directional knowledge transfer among tasks, we propose several techniques (continual prompt initialization, query fusion, and memory replay) to transfer knowledge from preceding tasks and a memory-guided technique to transfer knowledge from subsequent tasks. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method on continual learning for dialog state tracking, compared with state-of-the-art baselines.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Prompting & Reasoning, Dialogue & Conversational AI

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. Jun Zhu
3. Liyuan Wang
4. Xingxing Zhang
5. Lifu Huang
6. Jianguo Sun
7. Yongbin Li
8. Chang Gao

In Computer Vision and Pattern Recognition

1. Hang Su
2. Jun Zhu
3. Liyuan Wang
4. Xingxing Zhang
5. Jianguo Sun
6. Yongbin Li
7. Chang Gao
8. Ying Zhao

In Prompting & Reasoning

1. Liyuan Wang
2. Jun Zhu
3. Hang Su
4. Lifu Huang
5. Xingxing Zhang

Citations in the corpus

• A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “For example, a pre-trained transformer can effectively accommodate downstream tasks by learning only a few task-specific parameters, including adaptor-tuning [165] with inserted fully-connected layers (CTR [208], B-CL [209], CLASSIC [207], CPT [205], CLIF [190], AdapterCL [282], ACM [499], ADA [111]”
• Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection (2022, background): “Zhu et al. (2022) propose continual prompt tuning for dialogue state tracking.”
• Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey (2024, methodology): “Therefore, it’s natural to leverage PEFT methods for CL tasks [128], [238], [33], [110].”
• Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue (2022, background): “Some recent studies employ prompt tuning on continual learning for dialogue state tracking (Zhu et al., 2022) and few-shot learning (Qin and Joty, 2022).”