WHAT, WHEN, and HOW to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialogue
This work addresses the challenge of creating engaging, user persona-aware conversational agents for commercial applications, representing an incremental improvement in personalized dialogue systems.
The paper tackled the problem of designing personalized open-domain dialogue systems to address the WHAT, WHEN, and HOW (WWH) issues in natural response generation, resulting in more fluent conversations as shown by human and objective evaluations.
This paper presents a method for building a personalized open-domain dialogue system to address the WWH (WHAT, WHEN, and 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 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.