This paper presents a method for building a personalized open-domain dialogue system to address the $\textit{WWH}$ ($\textit{WHAT}$, $\textit{WHEN}$, and $\textit{HOW}$) problem for natural response generation in a commercial setting, where personalized dialogue responses are heavily interleaved with casual response turns. The proposed approach involves weighted dataset blending, negative persona information augmentation methods, and the design of personalized conversation datasets to address the challenges of $\textit{WWH}$ in personalized, open-domain dialogue systems. Our work effectively balances dialogue fluency and tendency to ground, while also introducing a response-type label to improve the controllability and explainability of the grounded responses. The combination of these methods leads to more fluent conversations, as evidenced by subjective human evaluations as well as objective evaluations.

翻译：本文提出了一种构建个性化开放域对话系统的方法，以解决商业场景中自然响应生成的$\textit{WWH}$（$\textit{WHAT}$、$\textit{WHEN}$和$\textit{HOW}$）问题。在该场景中，个性化对话响应与随意响应回合高度交织。所提出的方法包括加权数据集混合、负面画像信息增强技术以及个性化对话数据集的设计，以应对个性化开放域对话系统中$\textit{WWH}$的挑战。我们的工作有效平衡了对话流畅性与接地倾向，同时引入响应类型标签以提升接地响应的可控性和可解释性。这些方法的结合使得对话更加流畅，主观人工评估和客观评估均验证了这一点。