Usporedite metode

	Višejezični ugrađeni prikazi rečenica	Višejezična klasifikacija utemeljena na modelu RoBERTa
Područje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning
Godina nastanka	2019–2022	2020
Tvorac	Reimers, N. & Gurevych, I.; Feng, F. et al. (Google)	Conneau, A. et al. (Facebook AI Research)
Vrsta	Cross-lingual representation learning	Pretrained multilingual transformer fine-tuned for classification
Temeljni izvor	Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525.	Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzman, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020). Unsupervised Cross-lingual Representation Learning at Scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), pp. 8440–8451.
Drugi nazivi	multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings	XLM-RoBERTa classification, mRoBERTa, cross-lingual RoBERTa classifier, multilingual transformer classification
Srodne	5	4
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.	Multilingual RoBERTa-based classification uses XLM-RoBERTa — a transformer pretrained on 100+ languages via masked language modeling — and fine-tunes it on labeled text to assign categories across multiple languages. By sharing a single model across languages, it enables robust cross-lingual and zero-shot text classification without needing separate per-language classifiers.