Papers by Kathryn Kazanas

Copied to clipboard

Challenge:	Existing work on medical text simplification has focused on monolingual settings . important findings in medicine are typically presented in technical, jargon-laden language . text simulating models can generate viable simplified texts, but there are outstanding challenges .
Approach:	They propose a dataset for medical text simplification in four languages . they evaluate fine-tuned and zero-shot models across these languages based on human assessments and analyses .
Outcome:	The proposed dataset evaluates models in English, Spanish, French, and Farsi . it shows that the models can generate viable simplified texts, but there are challenges .