Your browser doesn't support javascript.
loading
Exploiting Unlabeled Texts with Clustering-based Instance Selection for Medical Relation Classification.
Kim, Youngjun; Riloff, Ellen; Meystre, Stéphane M.
Afiliación
  • Kim Y; School of Computing, University of Utah, Salt Lake City, UT, USA.
  • Riloff E; School of Computing, University of Utah, Salt Lake City, UT, USA.
  • Meystre SM; Medical University of South Carolina, Charleston, SC.
AMIA Annu Symp Proc ; 2017: 1060-1069, 2017.
Article en En | MEDLINE | ID: mdl-29854174
Classifying relations between pairs of medical concepts in clinical texts is a crucial task to acquire empirical evidence relevant to patient care. Due to limited labeled data and extremely unbalanced class distributions, medical relation classification systems struggle to achieve good performance on less common relation types, which capture valuable information that is important to identify. Our research aims to improve relation classification using weakly supervised learning. We present two clustering-based instance selection methods that acquire a diverse and balanced set of additional training instances from unlabeled data. The first method selects one representative instance from each cluster containing only unlabeled data. The second method selects a counterpart for each training instance using clusters containing both labeled and unlabeled data. These new instance selection methods for weakly supervised learning achieve substantial recall gains for the minority relation classes compared to supervised learning, while yielding comparable performance on the majority relation classes.
Asunto(s)

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Almacenamiento y Recuperación de la Información / Registros Electrónicos de Salud / Aprendizaje Automático Supervisado Tipo de estudio: Prognostic_studies Límite: Humans Idioma: En Revista: AMIA Annu Symp Proc Asunto de la revista: INFORMATICA MEDICA Año: 2017 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Estados Unidos

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Almacenamiento y Recuperación de la Información / Registros Electrónicos de Salud / Aprendizaje Automático Supervisado Tipo de estudio: Prognostic_studies Límite: Humans Idioma: En Revista: AMIA Annu Symp Proc Asunto de la revista: INFORMATICA MEDICA Año: 2017 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Estados Unidos