Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Tracking
This work addresses the challenge of costly annotation in task-oriented dialogues by enhancing zero-shot DST, though it is incremental as it builds on existing in-context learning approaches.
The paper tackles the problem of zero-shot dialogue state tracking by introducing ParsingDST, an in-context learning method that uses semantic parsing with large language models to improve updating strategies, resulting in significant improvements in Joint Goal Accuracy and slot accuracy on MultiWOZ compared to existing methods.
Zero-shot Dialogue State Tracking (DST) addresses the challenge of acquiring and annotating task-oriented dialogues, which can be time-consuming and costly. However, DST extends beyond simple slot-filling and requires effective updating strategies for tracking dialogue state as conversations progress. In this paper, we propose ParsingDST, a new In-Context Learning (ICL) method, to introduce additional intricate updating strategies in zero-shot DST. Our approach reformulates the DST task by leveraging powerful Large Language Models (LLMs) and translating the original dialogue text to JSON through semantic parsing as an intermediate state. We also design a novel framework that includes more modules to ensure the effectiveness of updating strategies in the text-to-JSON process. Experimental results demonstrate that our approach outperforms existing zero-shot DST methods on MultiWOZ, exhibiting significant improvements in Joint Goal Accuracy (JGA) and slot accuracy compared to existing ICL methods. Our code has been released.