Context Aggregation with Topic-focused Summarization for Personalized Medical Dialogue Generation

Page view(s)
3
Checked on Nov 10, 2024
Context Aggregation with Topic-focused Summarization for Personalized Medical Dialogue Generation
Title:
Context Aggregation with Topic-focused Summarization for Personalized Medical Dialogue Generation
Journal Title:
Proceedings of the 6th Clinical Natural Language Processing Workshop
Keywords:
Publication Date:
01 July 2024
Citation:
Zhengyuan Liu, Siti Salleh, Pavitra Krishnaswamy, and Nancy Chen. 2024. Context Aggregation with Topic-focused Summarization for Personalized Medical Dialogue Generation. In Proceedings of the 6th Clinical Natural Language Processing Workshop, pages 310–321, Mexico City, Mexico. Association for Computational Linguistics.
Abstract:
In the realm of dialogue systems, generated responses often lack personalization. This is particularly true in the medical domain, where research is limited by scarce available domain-specific data and the complexities of modeling medical context and persona information. In this work, we investigate the potential of harnessing large language models for personalized medical dialogue generation. In particular, to better aggregate the long conversational context, we adopt topic-focused summarization to distill core information from the dialogue history, and use such information to guide the conversation flow and generated content. Drawing inspiration from real-world telehealth conversations, we outline a comprehensive pipeline encompassing data processing, profile construction, and domain adaptation. This work not only highlights our technical approach but also shares distilled insights from the data preparation and model construction phases.
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This research / project is supported by the I2R, Agency for Science, Technology and Research (A*STAR) - Diabetes Clinic of the Future (DCOF)
Grant Reference no. : H19/01/a0/023
Description:
ISBN:
10.18653/v1/2024.clinicalnlp-1.27