每次解雇一名对话设计师，对话系统的性能就会下降
Every time I fire a conversational designer, the performance of the dialog system goes down
AI总结：
本文提出对话逻辑注入神经网络系统（CLINN），通过评估不同技能对话设计师的半逻辑规则，发现其能显著减少标注需求且性能优于最先进神经对话系统，证实对话设计师显式领域知识的重要性。
摘要：
将显式领域知识融入基于神经的任务导向对话系统是减少对大规模标注对话集需求的有效方法。本文研究对话设计师的显式领域知识使用如何影响基于神经的对话系统性能。为支持该研究，我们提出对话逻辑注入神经网络系统（CLINN），其中显式知识以半逻辑规则编码。通过CLINN，我们评估了不同技能水平对话设计师团队生成的半逻辑规则。我们在MultiWOZ数据集的Restaurant主题上进行实验。结果表明，外部知识对减少对话系统对标注示例的需求极为重要；CLINN中使用的对话设计师规则显著优于最先进的基于神经的对话系统。
英文摘要：
Incorporating explicit domain knowledge into neural-based task-oriented dialogue systems is an effective way to reduce the need of large sets of annotated dialogues. In this paper, we investigate how the use of explicit domain knowledge of conversational designers affects the performance of neural-based dialogue systems. To support this investigation, we propose the Conversational-Logic-Injection-in-Neural-Network system (CLINN) where explicit knowledge is coded in semi-logical rules. By using CLINN, we evaluated semi-logical rules produced by a team of differently skilled conversational designers. We experimented with the Restaurant topic of the MultiWOZ dataset. Results show that external knowledge is extremely important for reducing the need of annotated examples for conversational systems. In fact, rules from conversational designers used in CLINN significantly outperform a state-of-the-art neural-based dialogue system.
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。
