Uporedite metode

	Adaptivno modelovanje tema	BERT-based Classification
Oblast	Duboko učenje	Duboko učenje
Porodica	Machine learning	Machine learning
Godina nastanka	2020–2022	2019
Tvorac	Bianchi et al.; Grootendorst, M.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language)
Tip	Fine-tuned neural topic model	Pre-trained language model with fine-tuning
Temeljni izvor	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.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics.
Drugi nazivi	neural topic modeling, fine-tuned topic model, pre-trained topic model, contextual topic modeling	BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS
Srodne	6	4
Sažetak	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.	BERT-based Classification fine-tunes Google's Bidirectional Encoder Representations from Transformers model on a labelled text dataset, replacing the generic pre-trained head with a task-specific classification layer. It exploits deep bidirectional context from hundreds of millions of pre-trained parameters to deliver state-of-the-art accuracy on short- and medium-length text classification tasks with relatively modest amounts of labelled data.