Building a Personalized Dialogue System with Prompt-Tuning

2022/06/11 by Tomohito Kasahara, Kasahara, Tomohito, Daisuke Kawahara +10
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.2206.05399

Accepted to NAACL 2022 SRW

arxiv created 2022/06/11 · openalex publication_date 2022/06/11 · arxiv updated 2022/06/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Dialogue systems without consistent responses are not fascinating. In this study, we build a dialogue system that can respond based on a given character setting (persona) to bring consistency. Considering the trend of the rapidly increasing scale of language models, we propose an approach that uses prompt-tuning, which has low learning costs, on pre-trained large-scale language models. The results of automatic and manual evaluations in English and Japanese show that it is possible to build a dialogue system with more natural and personalized responses using less computational resources than fine-tuning.

Related

• "In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
• A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data
• SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation
• PersoBench: Benchmarking Personalized Response Generation in Large Language Models
• Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models