A Dual Prompt Learning Framework for Few-Shot Dialogue State Tracking
This work addresses the challenge of low-resource DST for developers of task-oriented dialog systems, offering an incremental improvement through a novel prompt-based method.
The paper tackles the problem of costly data labeling for dialogue state tracking (DST) in task-oriented dialog systems by proposing a dual prompt learning framework that leverages pre-trained language models for few-shot DST, achieving state-of-the-art performance on two datasets and enabling generation of unseen slots.
Dialogue state tracking (DST) module is an important component for task-oriented dialog systems to understand users' goals and needs. Collecting dialogue state labels including slots and values can be costly, especially with the wide application of dialogue systems in more and more new-rising domains. In this paper, we focus on how to utilize the language understanding and generation ability of pre-trained language models for DST. We design a dual prompt learning framework for few-shot DST. Specifically, we consider the learning of slot generation and value generation as dual tasks, and two prompts are designed based on such a dual structure to incorporate task-related knowledge of these two tasks respectively. In this way, the DST task can be formulated as a language modeling task efficiently under few-shot settings. Experimental results on two task-oriented dialogue datasets show that the proposed method not only outperforms existing state-of-the-art few-shot methods, but also can generate unseen slots. It indicates that DST-related knowledge can be probed from PLM and utilized to address low-resource DST efficiently with the help of prompt learning.