Usporedite metode

	Otkrivanje parafraza	BERT Embeddings
Područje	Rudarenje teksta	Rudarenje teksta
Obitelj	Process / pipeline	Process / pipeline
Godina nastanka	—	2019
Tvorac	—	Devlin, Chang, Lee & Toutanova (Google AI)
Vrsta	NLP sentence-pair classification task	Contextual transformer text-representation method
Temeljni izvor	Dolan, W. B. & Brockett, C. (2005). Automatically Constructing a Corpus of Sentential Paraphrases. Proceedings of the Third International Workshop on Paraphrasing (IWP).	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.
Drugi nazivi	Parafroz Tespiti (Paraphrase Detection), paraphrase identification, semantic equivalence detection	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri
Srodne	4	4
Sažetak	Paraphrase detection is a natural-language-processing task that decides whether two sentences expressed in different wordings carry the same meaning. The task and its benchmark resources were established by Dolan and Brockett (2005), and it underpins plagiarism detection, question matching, and data deduplication.	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.