Usporedite metode

	BERT Embeddings	Klasifikacija teksta	Prijenosno učenje
Područje	Rudarenje teksta	Rudarenje teksta	Strojno učenje
Obitelj	Process / pipeline	Process / pipeline	Machine learning
Godina nastanka	2019	—	2010 (formalized); 1990s (early roots)
Tvorac	Devlin, Chang, Lee & Toutanova (Google AI)	—	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Vrsta	Contextual transformer text-representation method	Supervised NLP classification task	Learning paradigm
Temeljni izvor	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.	Joachims, T. (1998). Text Categorization with Support Vector Machines: Learning with Many Relevant Features. ECML 1998. Lecture Notes in Computer Science, vol 1398. Springer.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Drugi nazivi	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri	text categorization, document classification, topic classification, metin sınıflandırma	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Srodne	4	4	3
Sažetak	BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA.	Text classification, also called text categorization, is a supervised natural-language-processing task that automatically assigns documents to predefined categories. Building on the support-vector-machine approach to text categorization established by Joachims (1998) and consolidated in the text-mining literature by Aggarwal and Zhai (2012), it powers tasks such as spam detection and topic classification by learning from labelled examples.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.