零样本对话理解新框架，无需预设槽位值即可动态适应新场景。
A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding
- 将对话状态追踪重构为问答任务，适配低算力模型。
- 在Multi-WOZ 2.1上实现20%的联合目标准确率提升。
- 仅需原方法90%的API调用次数，适合资源受限场景。
对话状态追踪（DST）对理解用户需求并执行相应系统动作至关重要。现有方法多依赖预定义本体且需真实领域标签，在应对新槽位值时表现不佳。基于大语言模型的零样本方法虽有潜力，但或需大量计算资源，或性能落后于全训练模型，实用性受限。为此，我们提出一种零样本、开放词汇的统一管道系统，整合领域分类与DST。方法包括将DST重构成问答任务以降低模型要求，并对高适应性模型使用自优化提示。系统不依赖本体中固定的槽位值，可动态适应。实验表明，在Multi-WOZ 2.1等数据集上，相比现有最先进方法，该系统在联合目标准确率（JGA）上最高提升20%，同时减少高达90%的LLM API请求。
原文摘要 · Abstract (English)
Dialogue State Tracking (DST) is crucial for understanding user needs and executing appropriate system actions in task-oriented dialogues. Majority of existing DST methods are designed to work within predefined ontologies and assume the availability of gold domain labels, struggling with adapting to new slots values. While Large Language Models (LLMs)-based systems show promising zero-shot DST performance, they either require extensive computational resources or they underperform existing fully-trained systems, limiting their practicality. To address these limitations, we propose a zero-shot, open-vocabulary system that integrates domain classification and DST in a single pipeline. Our approach includes reformulating DST as a question-answering task for less capable models and employing self-refining prompts for more adaptable ones. Our system does not rely on fixed slot values defined in the ontology allowing the system to adapt dynamically. We compare our approach with existing SOTA, and show that it provides up to 20% better Joint Goal Accuracy (JGA) over previous methods on datasets like Multi-WOZ 2.1, with up to 90% fewer requests to the LLM API.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。