利用知识寻求轮次为描述驱动的对话状态跟踪器提供基础
Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns
AI总结：
针对模式引导对话状态跟踪器易受模式写作风格影响的问题，本文提出在微调和推理提示中加入对话语料库中的知识寻求轮次，从而在 SGD 和 SGD-X 上显著提升鲁棒性。
摘要：
基于模式引导的对话状态跟踪器无需进一步训练即可泛化到新领域，但它们对模式的写作风格很敏感。使用人工或合成的模式释义来增强训练集，可以提高模型对这些变化的鲁棒性，但这样做可能成本高昂或难以控制。我们提出通过让状态跟踪模型同时基于从对话语料库中收集的知识寻求轮次和模式来规避这些问题。在微调和推理期间将这些轮次纳入提示中，可显著提升模型的鲁棒性，这一点在 SGD 和 SGD-X 上平均联合目标准确率和模式敏感性的大幅提升中得到了证明。
英文摘要：
Schema-guided dialogue state trackers can generalise to new domains without further training, yet they are sensitive to the writing style of the schemata. Augmenting the training set with human or synthetic schema paraphrases improves the model robustness to these variations but can be either costly or difficult to control. We propose to circumvent these issues by grounding the state tracking model in knowledge-seeking turns collected from the dialogue corpus as well as the schema. Including these turns in prompts during finetuning and inference leads to marked improvements in model robustness, as demonstrated by large average joint goal accuracy and schema sensitivity improvements on SGD and SGD-X.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
