SMILE: Single-turn To Multi-turn Inclusive Language Expansion Via Chatgpt For Mental Health Support
Huachuan Qiu, Hongliang He, Shuai Zhang, Anqi Li, Zhenzhong Lan. Arxiv 2023
[Paper]
Developing specialized dialogue systems for mental health support requires multi-turn conversation data, which has recently garnered increasing attention. However, gathering and releasing large-scale and real-life multi-turn conversations to facilitate advancements in mental health presents challenges due to data privacy protection, as well as the time and cost involved. To address the challenges related to data scarcity, we introduce SMILE, a single-turn to multi-turn inclusive language expansion technique that prompts ChatGPT to rewrite public single-turn dialogues into multi-turn ones. Our work begins with the analysis of language transformation, validating the feasibility of the proposed method when compared with other baseline methods. We then conduct a study on dialogue diversity, including lexical features, semantic features, and dialogue topics, demonstrating the effectiveness of our proposed method. Furthermore, we implement an expert evaluation and the results demonstrate that the dialogues generated with our proposed method are of higher quality than those generated with other baseline methods. Thus, we employ our method to generate a large-scale, diverse, and high-quality dialogue dataset named SmileChat, comprising 55,165 dialogues in total with an average of 10.4 turns per dialogue. Finally, we utilize the collected corpus to develop a mental health chatbot, MeChat. To better assess the overall quality of SmileChat, we collect a real-life chat dataset comprising 82 counseling dialogues for model evaluation. Both automatic and human evaluations demonstrate that our trained dialogue system exhibits significant improvements, showcasing that SmileChat is high-quality and practical.
Similar Work