Using Structured Health Information for Controlled Generation of Clinical Cases in French - Laboratoire Interdisciplinaire des Sciences du Numérique Access content directly
Conference Papers Year : 2024

Using Structured Health Information for Controlled Generation of Clinical Cases in French

Abstract

Text generation opens up new prospects for overcoming the lack of open corpora in fields such as healthcare, where data sharing is bound by confidentiality. In this study, we compare the performance of encoder-decoder and decoder-only language models for the controlled generation of clinical cases in French. To do so, we fine-tuned several pre-trained models on French clinical cases for each architecture and generate clinical cases conditioned by patient demographic information (gender and age) and clinical features. Our results suggest that encoder-decoder models are easier to control than decoder-only models, but more
Fichier principal
Vignette du fichier
Codeine_clinicalNLP.pdf (231.25 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04558890 , version 1 (25-04-2024)

Identifiers

  • HAL Id : hal-04558890 , version 1

Cite

Hugo Boulanger, Nicolas Hiebel, Olivier Ferret, Karën Fort, Aurélie Névéol. Using Structured Health Information for Controlled Generation of Clinical Cases in French. The 6th Clinical Natural Language Processing Workshop At NAACL 2024 (ClinicalNLP 2024), Jun 2024, Mexico city, Mexico. ⟨hal-04558890⟩
126 View
52 Download

Share

Gmail Mastodon Facebook X LinkedIn More