השוואת שיטות

	שיפור הטמעות משפטים מותאמות תחום	שיכוני משפטים רב-לשוניים
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2019–2020	2019–2022
הוגה השיטה	Reimers, N. & Gurevych, I. (Sentence-BERT); Gururangan et al. (domain-adaptive pretraining)	Reimers, N. & Gurevych, I.; Feng, F. et al. (Google)
סוג	Domain-adaptive representation learning	Cross-lingual representation learning
מקור מכונן	Reimers, N. & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of EMNLP-IJCNLP 2019, pp. 3982–3992.	Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525.
כינויים	domain-adapted sentence transformers, domain-specific sentence embeddings, target-domain sentence representations, DAPT sentence embeddings	multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings
קשורות	6	5
תקציר	Domain-adaptive sentence embeddings extend general-purpose sentence encoders — such as Sentence-BERT — by continuing their training on domain-specific text. The result is a fixed-length vector representation that captures both universal language understanding and the vocabulary, style, and semantic nuances of the target domain, improving downstream NLP tasks such as semantic search, clustering, and classification.	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.