Cargando...

Learning Disentangled Representations of Texts with Application to Biomedical Abstracts

We propose a method for learning disentangled representations of texts that code for distinct and complementary aspects, with the aim of affording efficient model transfer and interpretability. To induce disentangled embeddings, we propose an adversarial objective based on the (dis)similarity betwee...

Descrición completa

Gardado en:
Detalles Bibliográficos
Publicado en:Proc Conf Empir Methods Nat Lang Process
Main Authors: Jain, Sarthak, Banner, Edward, van de Meent, Jan-Willem, Marshall, Iain J., Wallace, Byron C.
Formato: Artigo
Idioma:Inglês
Publicado: 2018
Assuntos:
Acceso en liña:https://ncbi.nlm.nih.gov/pmc/articles/PMC8136418/
https://ncbi.nlm.nih.gov/pubmed/34027519
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.18653/v1/d18-1497
Tags: Engadir etiqueta
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!