Care4Lang at MEDIQA-Chat 2023: Fine-tuning Language Models for Classifying and Summarizing Clinical Dialogues

Amal Alqahtani, Rana Salama, Mona Diab, Abdou Youssef


Abstract
Summarizing medical conversations is one of the tasks proposed by MEDIQA-Chat to promote research on automatic clinical note generation from doctor-patient conversations. In this paper, we present our submission to this task using fine-tuned language models, including T5, BART and BioGPT models. The fine-tuned models are evaluated using ensemble metrics including ROUGE, BERTScore andBLEURT. Among the fine-tuned models, Flan-T5 achieved the highest aggregated score for dialogue summarization.
Anthology ID:
2023.clinicalnlp-1.55
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:
524–528
Language:
URL:
https://aclanthology.org/2023.clinicalnlp-1.55
DOI:
10.18653/v1/2023.clinicalnlp-1.55
Bibkey:
Cite (ACL):
Amal Alqahtani, Rana Salama, Mona Diab, and Abdou Youssef. 2023. Care4Lang at MEDIQA-Chat 2023: Fine-tuning Language Models for Classifying and Summarizing Clinical Dialogues. In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 524–528, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Care4Lang at MEDIQA-Chat 2023: Fine-tuning Language Models for Classifying and Summarizing Clinical Dialogues (Alqahtani et al., ClinicalNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.clinicalnlp-1.55.pdf