Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation

Jian Wang, Yi Cheng, Dongding Lin, Chak Tou Leong, Wenjie Li

Submission Type: Regular Short Paper

Submission Track: Dialogue and Interactive Systems

Submission Track 2: Dialogue and Interactive Systems

Keywords: Target-oriented dialogue, Proactive dialogue, Personalization, Dataset curation

Abstract: Target-oriented dialogue systems, designed to proactively steer conversations toward predefined targets or accomplish specific system-side goals, are an exciting area in conversational AI. In this work, by formulating a <dialogue act, topic> pair as the conversation target, we explore a novel problem of personalized target-oriented dialogue by considering personalization during the target accomplishment process. However, there remains an emergent need for high-quality datasets, and building one from scratch requires tremendous human effort. To address this, we propose an automatic dataset curation framework using a role-playing approach. Based on this framework, we construct a large-scale personalized target-oriented dialogue dataset, TopDial, which comprises about 18K multi-turn dialogues. The experimental results show that this dataset is of high quality and could contribute to exploring personalized target-oriented dialogue.

Submission Number: 1553