ScholarGate
Asisten
Machine learningDeep learning / NLP / CV

Model Topik NMF Swasupervisi

Model Topik NMF Swasupervisi memperluas Faktorisasi Matriks Non-negatif klasik untuk penemuan topik dengan menggabungkan sinyal pembelajaran swasupervisi — seperti rekonstruksi kata yang disamarkan atau tujuan kontrastif — ke dalam optimasi NMF, menghasilkan topik yang lebih koheren dan bermakna secara semantik dari korpus teks tanpa memerlukan data berlabel manusia.

Buka di MethodMindSegeraVideoSegeraDownload slides

Baca metode selengkapnya

Khusus anggota

Masuk dengan akun gratis untuk membaca bagian ini.

Masuk

Method map

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

Sumber

  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

Cara menyitasi halaman ini

ScholarGate. (2026, June 3). Self-supervised Non-negative Matrix Factorization Topic Model. ScholarGate. https://scholargate.app/id/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). Diakses 2026-06-15 dari https://scholargate.app/id/deep-learning/self-supervised-nmf-topic-model · Set data: https://doi.org/10.5281/zenodo.20539026