Comparer des méthodes

	Embeddings BERT	Analyse de collocations
Domaine	Fouille de textes	Fouille de textes
Famille	Process / pipeline	Process / pipeline
Année d'origine	2019	1990
Auteur d'origine	Devlin, Chang, Lee & Toutanova (Google AI)	Church & Hanks
Type	Contextual transformer text-representation method	Statistical text-mining technique
Source fondatrice	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.	Church, K.W. & Hanks, P. (1990). Word Association Norms, Mutual Information, and Lexicography. Computational Linguistics, 16(1), 22-29.
Alias	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri	word association, collocation extraction, Birliktelik Analizi (Collocation Analysis)
Apparentées	4	3
Résumé	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.	Collocation analysis is a statistical text-mining technique that identifies word pairs or expressions that frequently occur together, using association measures rather than chance co-occurrence. Introduced in the lexicography work of Church and Hanks (1990), it is used for terminology extraction and language analysis, surfacing the multi-word units that carry meaning in a corpus.