Vertaile menetelmiä

	Semanttinen samankaltaisuus – Merkityksen mittaaminen tekstien välillä	BERT-upotukset – kontekstisidonnaiset tekstiesitykset	TF-IDF
Tieteenala	Tekstinlouhinta	Tekstinlouhinta	Tekstinlouhinta
Menetelmäperhe	Process / pipeline	Process / pipeline	Process / pipeline
Syntyvuosi	2019	2019	1988
Kehittäjä	Nils Reimers & Iryna Gurevych (Sentence-BERT)	Devlin, Chang, Lee & Toutanova (Google AI)	Salton & Buckley
Tyyppi	NLP text-comparison task	Contextual transformer text-representation method	Text vectorization / term-weighting scheme
Alkuperäislähde	Reimers, N. & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. EMNLP.	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.	Salton, G. & Buckley, C. (1988). Term-weighting approaches in automatic text retrieval. Information Processing & Management, 24(5), 513-523.
Rinnakkaisnimet	semantic textual similarity, text similarity, Anlamsal Benzerlik Analizi	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri	term weighting, tf-idf weighting, TF-IDF Vektörizasyonu
Liittyvät	4	4	3
Tiivistelmä	Semantic similarity analysis measures how close in meaning two texts are, rather than how many words they share on the surface. Building on the Sentence-BERT work of Reimers and Gurevych (2019), it represents each text as a vector and compares those vectors so that paraphrases score high even when their wording differs.	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.	TF-IDF, introduced by Salton and Buckley (1988), is a term-weighting scheme that scores each word in a document by how often it appears there and how rare it is across the whole collection. It turns raw text into weighted document vectors, giving high weight to terms that are frequent in one document but uncommon elsewhere.