Usporedite metode

	Domenski prilagođene ugradnje rečenica	BERT-tem klasifikacija
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2019–2020	2019
Tvorac	Reimers, N. & Gurevych, I. (Sentence-BERT); Gururangan et al. (domain-adaptive pretraining)	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language)
Vrsta	Domain-adaptive representation learning	Pre-trained language model with fine-tuning
Temeljni izvor	Reimers, N. & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of EMNLP-IJCNLP 2019, pp. 3982–3992.	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	domain-adapted sentence transformers, domain-specific sentence embeddings, target-domain sentence representations, DAPT sentence embeddings	BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS
Srodne	6	4
Sažetak	Domain-adaptive sentence embeddings extend general-purpose sentence encoders — such as Sentence-BERT — by continuing their training on domain-specific text. The result is a fixed-length vector representation that captures both universal language understanding and the vocabulary, style, and semantic nuances of the target domain, improving downstream NLP tasks such as semantic search, clustering, and classification.	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.