Modeling Low-Resource Health Coaching Dialogues via Neuro-Symbolic Goal Summarization and Text-Units-Text Generation
This work addresses the cost-prohibitive nature of personalized health coaching for low-resource populations, offering an incremental improvement in automating coaching dialogues.
The paper tackles the problem of making health coaching more accessible for low-socioeconomic populations by developing neuro-symbolic goal summarization and text-units-text generation models to automate dialogue and goal tracking, outperforming previous state-of-the-art methods without needing predefined schema.
Health coaching helps patients achieve personalized and lifestyle-related goals, effectively managing chronic conditions and alleviating mental health issues. It is particularly beneficial, however cost-prohibitive, for low-socioeconomic status populations due to its highly personalized and labor-intensive nature. In this paper, we propose a neuro-symbolic goal summarizer to support health coaches in keeping track of the goals and a text-units-text dialogue generation model that converses with patients and helps them create and accomplish specific goals for physical activities. Our models outperform previous state-of-the-art while eliminating the need for predefined schema and corresponding annotation. We also propose a new health coaching dataset extending previous work and a metric to measure the unconventionality of the patient's response based on data difficulty, facilitating potential coach alerts during deployment.