A text style transfer system for reducing the physician–patient expertise gap: An analysis with automatic and human evaluations

Luca Bacco, Felice Dell'Orletta, Huiyuan Lai, Mario Merone*, Malvina Nissim

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

5 Citations (Scopus)
149 Downloads (Pure)

Abstract

Physicians and patients often come from different backgrounds and have varying levels of education, which can result in communication difficulties in the healthcare process. To address this expertise gap, we present a “Text Style Transfer” system. Our system uses Semantic Textual Similarity techniques based on Sentence Transformers models to create pseudo-parallel datasets from a large, non-parallel corpus of lay and expert texts. This approach allowed us to train a denoising autoencoder model (BART), overcoming the limitations of previous systems. Our extensive analysis, which includes both automatic metrics and human evaluations from both lay (patients) and expert (physicians) individuals, shows that our system outperforms state-of-the-art models and is comparable to human-provided gold references in some cases.

Original languageEnglish
Article number120874
Number of pages18
JournalExpert systems with applications
Volume233
DOIs
Publication statusPublished - 15-Dec-2023

Keywords

  • Healthcare
  • Natural language processing
  • Semantic textual similarity
  • Text simplification
  • Text style transfer

Fingerprint

Dive into the research topics of 'A text style transfer system for reducing the physician–patient expertise gap: An analysis with automatic and human evaluations'. Together they form a unique fingerprint.

Cite this