WHAT, WHEN, and HOW to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialogue

TL;DR

This paper introduces a novel method for building personalized open-domain dialogue systems that effectively balance fluency and grounding by leveraging dataset blending, persona augmentation, and response-type labeling, leading to more engaging and controllable conversations.

Contribution

It proposes a comprehensive approach combining dataset blending, persona augmentation, and response labeling to improve personalization and grounding in dialogue systems.

Findings

Enhanced dialogue fluency and grounding balance.

Improved controllability and explainability of responses.

Positive human and objective evaluation results.

Abstract

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.