Methoden vergelijken

	Domeinadaptatie	BERT-inbeddingen	Transferleren
Vakgebied	Tekstmining	Tekstmining	Machine learning
Familie	Process / pipeline	Process / pipeline	Machine learning
Jaar van ontstaan	—	2019	2010 (formalized); 1990s (early roots)
Grondlegger	—	Devlin, Chang, Lee & Toutanova (Google AI)	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Type	NLP transfer-learning / fine-tuning pipeline	Contextual transformer text-representation method	Learning paradigm
Oorspronkelijke bron	Lee, J. et al. (2020). BioBERT: A Pre-trained Biomedical Language Representation Model. Bioinformatics.	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Aliassen	Alan Uyarlaması (Domain Adaptation) — NLP, domain adaptation NLP, domain fine-tuning	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Verwant	4	4	3
Samenvatting	Domain adaptation is a natural-language-processing technique that takes a general pretrained language model and fine-tunes it on target-domain data so that it performs better in specialised fields such as medicine, law, and finance. It builds on the transfer-learning ideas behind work like Blitzer et al. (2007) on cross-domain sentiment classification and Lee et al. (2020) on the biomedical BioBERT model.	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.	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.