Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Přenosové učení s modelováním témat× | Modelování témat s doladěním× | |
|---|---|---|
| Obor | Hluboké učení | Hluboké učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2010s | 2020–2022 |
| Tvůrce≠ | Pan, S. J. & Yang, Q. (transfer learning survey); combined with Blei et al. (LDA, 2003) | Bianchi et al.; Grootendorst, M. |
| Typ≠ | Cross-domain adaptation of topic models | Fine-tuned neural topic model |
| Původní zdroj≠ | Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ | Bianchi, F., Terragni, S., Hovy, D., Nozza, D., & Fersini, E. (2021). Cross-lingual Contextualized Topic Models with Zero-shot Learning. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 1676–1683. DOI ↗ |
| Další názvy | domain-transfer topic modeling, pretrained topic transfer, cross-domain topic adaptation, TL-LDA | neural topic modeling, fine-tuned topic model, pre-trained topic model, contextual topic modeling |
| Příbuzné≠ | 5 | 6 |
| Shrnutí≠ | Transfer Learning with Topic Modeling adapts topic structures discovered on a large or well-labeled source corpus to a related but distinct target domain where labeled data or large corpora are scarce. By reusing source-domain topic priors or pretrained embeddings as initialization, the approach produces richer, more coherent topics in the target domain than training from scratch. | Fine-Tuned Topic Modeling adapts pre-trained language models — such as BERT or Sentence-BERT — to discover latent topics in document collections. Unlike classical probabilistic methods (LDA, NMF), it leverages rich contextual embeddings and optionally fine-tunes the backbone on domain-specific corpora, producing more coherent and semantically meaningful topics, especially on short texts or specialized domains. |
| ScholarGateDatová sada ↗ |
|
|