Improving natural language information extraction from cancer pathology reports using transfer learning and zero-shot string similarity

OBJECTIVE: We develop natural language processing (NLP) methods capable of accurately classifying tumor attributes from pathology reports given minimal labeled examples. Our hierarchical cancer to cancer transfer (HCTC) and zero-shot string similarity (ZSS) methods are designed to exploit shared inf...

Descripción completa

Detalles Bibliográficos
Autores principales: Park, Briton, Altieri, Nicholas, DeNero, John, Odisho, Anobel Y, Yu, Bin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2021
Materias:
Research and Applications
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8484934/
https://www.ncbi.nlm.nih.gov/pubmed/34604711
http://dx.doi.org/10.1093/jamiaopen/ooab085

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8484934/
https://www.ncbi.nlm.nih.gov/pubmed/34604711
http://dx.doi.org/10.1093/jamiaopen/ooab085

Ejemplares similares