The schema-guided paradigm overcomes scalability issues inherent in building task-oriented dialogue (TOD) agents with static ontologies. Instead of operating on dialogue context alone, agents have access to hierarchical schemas containing task-relevant natural language descriptions. Fine-tuned language models excel at schema-guided dialogue state tracking (DST) but are sensitive to the writing style of the schemas. We explore methods for improving the robustness of DST models. We propose a framework for generating synthetic schemas which uses tree-based ranking to jointly optimise lexical diversity and semantic faithfulness. The generalisation of strong baselines is improved when augmenting their training data with prompts generated by our framework, as demonstrated by marked improvements in average joint goal accuracy (JGA) and schema sensitivity (SS) on the SGD-X benchmark.

翻译：模式引导范式克服了基于静态本体构建任务导向型对话（TOD）智能体时固有的可扩展性问题。智能体无需仅依赖对话上下文，而是能够访问包含任务相关自然语言描述的层级化模式。微调语言模型在模式引导对话状态追踪（DST）中表现优异，但对模式的写作风格较为敏感。本文探索提升DST模型鲁棒性的方法，提出一种生成合成模式的框架，该框架通过树形排序联合优化词汇多样性与语义忠实度。实验表明，在SGD-X基准测试中，使用本框架生成的提示数据增强强基线模型的训练数据后，其泛化能力显著提升，平均联合目标准确率（JGA）与模式敏感性（SS）均有明显改善。