ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Semi-overvåget BERT-baseret Klassifikation

Semi-overvåget BERT-baseret klassifikation finjusterer en forudtrænet BERT-encoder på en lille pulje af mærkede tekstenheder, mens den samtidig udnytter en meget større mængde umærkede tekstenheder — via konsistenstræning, pseudo-mærkning eller dataaugmentation — for at producere klassifikatorer af høj kvalitet, selv når manuel annotering er knap.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

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

+3 more

Kilder

  1. Xie, Q., Dai, Z., Hovy, E., Luong, T., & Le, Q. (2020). Unsupervised Data Augmentation for Consistency Training. Advances in Neural Information Processing Systems (NeurIPS), 33, 27780–27792. link
  2. Chen, J., Yang, Z., & Yang, D. (2020). MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), 2147–2157. DOI: 10.18653/v1/2020.acl-main.194

Sådan citerer du denne side

ScholarGate. (2026, June 3). Semi-supervised BERT-based Text Classification. ScholarGate. https://scholargate.app/da/deep-learning/semi-supervised-bert-based-classification

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

Refereret af

ScholarGateSemi-supervised BERT-based Classification (Semi-supervised BERT-based Text Classification). Hentet 2026-06-15 fra https://scholargate.app/da/deep-learning/semi-supervised-bert-based-classification · Datasæt: https://doi.org/10.5281/zenodo.20539026