ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Zelf-gesuperviseerde NMF-onderwerpmodel

Het Self-supervised NMF Topic Model breidt klassieke Non-negative Matrix Factorization (NMF) voor topic discovery uit door self-supervised learning signalen – zoals masked-word reconstruction of contrastieve objectieven – te integreren in de NMF-optimalisatie, wat resulteert in coherentere en semantisch betekenisvollere topics uit tekstcorpora zonder dat er menselijk gelabelde data nodig is.

Openen in MethodMindBinnenkortVideoBinnenkortDownload slides

Lees de volledige methode

Alleen voor leden

Log in met een gratis account om dit onderdeel te lezen.

Inloggen

Method map

The neighbourhood of related methods — select a node to explore.

Zelf-gesuperviseerde NMF-onderwerpmodel
Latente Dirichlet Alloca…Niet-negatieve Matrixfac…

Bronnen

  1. Shi, T., Guo, X., Lv, J., & Yu, P. S. (2022). Self-supervised NMF-based graph contrastive learning for semi-supervised node classification. In Proceedings of the 36th AAAI Conference on Artificial Intelligence. link
  2. Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791. DOI: 10.1038/44565

Deze pagina citeren

ScholarGate. (2026, June 3). Self-supervised Non-negative Matrix Factorization Topic Model. ScholarGate. https://scholargate.app/nl/deep-learning/self-supervised-nmf-topic-model

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side
ScholarGateSelf-supervised NMF Topic Model (Self-supervised Non-negative Matrix Factorization Topic Model). Geraadpleegd op 2026-06-15 via https://scholargate.app/nl/deep-learning/self-supervised-nmf-topic-model · Gegevensset: https://doi.org/10.5281/zenodo.20539026