Continual Prompt Tuning for Dialog State Tracking
This addresses the problem of adapting dialog systems to new domains without forgetting old skills, which is incremental as it builds on existing prompt tuning methods.
The paper tackles catastrophic forgetting in continual learning for dialog state tracking by introducing Continual Prompt Tuning, a parameter-efficient framework that avoids forgetting and enables knowledge transfer between tasks, achieving strong performance compared to state-of-the-art baselines.
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.