Uporedite metode

	Višejezični ugrađeni prikazi rečenica (Multilingual sentence embeddings)	Преносно учење са уграђивањем реченица
Oblast	Duboko učenje	Duboko učenje
Porodica	Machine learning	Machine learning
Godina nastanka	2019–2022	2017–2019
Tvorac	Reimers, N. & Gurevych, I.; Feng, F. et al. (Google)	Reimers, N. & Gurevych, I. (SBERT); Conneau, A. et al. (InferSent)
Tip	Cross-lingual representation learning	Transfer learning / sentence representation
Temeljni izvor	Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525.	Reimers, N. & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3982–3992.
Drugi nazivi	multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings	sentence embedding transfer learning, pre-trained sentence encoder fine-tuning, SBERT transfer learning, sentence representation transfer
Srodne	5	5
Sažetak	Multilingual sentence embeddings map sentences from many languages into a single shared vector space so that semantically equivalent sentences — regardless of language — land close together. Models such as LaBSE, multilingual Sentence-BERT, and mUSE have made it practical to compare, retrieve, and classify text across 50 to 100+ languages without translating anything first.	Transfer Learning with Sentence Embeddings takes a large pre-trained encoder — such as Sentence-BERT or the Universal Sentence Encoder — that already encodes general language knowledge into fixed-length vectors, and adapts it to a new task or domain with little additional labelled data. The pre-trained representations give a head start that often outperforms task-specific models trained from scratch on modest corpora.