DS4DH at MEDIQA-Chat 2023: Leveraging SVM and GPT-3 Prompt Engineering for Medical Dialogue Classification and Summarization

Boya Zhang, Rahul Mishra, Douglas Teodoro


Abstract
This paper presents the results of the Data Science for Digital Health (DS4DH) group in the MEDIQA-Chat Tasks at ACL-ClinicalNLP 2023. Our study combines the power of a classical machine learning method, Support Vector Machine, for classifying medical dialogues, along with the implementation of one-shot prompts using GPT-3.5. We employ dialogues and summaries from the same category as prompts to generate summaries for novel dialogues. Our findings exceed the average benchmark score, offering a robust reference for assessing performance in this field.
Anthology ID:
2023.clinicalnlp-1.57
Volume:
Proceedings of the 5th Clinical Natural Language Processing Workshop
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Tristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Anna Rumshisky
Venue:
ClinicalNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
536–545
Language:
URL:
https://aclanthology.org/2023.clinicalnlp-1.57
DOI:
10.18653/v1/2023.clinicalnlp-1.57
Bibkey:
Cite (ACL):
Boya Zhang, Rahul Mishra, and Douglas Teodoro. 2023. DS4DH at MEDIQA-Chat 2023: Leveraging SVM and GPT-3 Prompt Engineering for Medical Dialogue Classification and Summarization. In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 536–545, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
DS4DH at MEDIQA-Chat 2023: Leveraging SVM and GPT-3 Prompt Engineering for Medical Dialogue Classification and Summarization (Zhang et al., ClinicalNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.clinicalnlp-1.57.pdf