Krahasoni metodat

	Transformer Multilingual	Embeddings të fjalive shumëgjuhëshe
Fusha	Mësimi i thellë	Mësimi i thellë
Familja	Machine learning	Machine learning
Viti i origjinës	2019–2020	2019–2022
Krijuesi	Devlin et al. (mBERT); Conneau et al. (XLM-R)	Reimers, N. & Gurevych, I.; Feng, F. et al. (Google)
Lloji	Pre-trained cross-lingual language model	Cross-lingual representation learning
Burimi themelues	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, pp. 4171–4186. Association for Computational Linguistics.	Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525.
Emërtime të tjera	multilingual LM, cross-lingual transformer, mBERT-style model, multilingual pre-trained model	multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings
Të lidhura	4	5
Përmbledhja	A multilingual transformer is a pre-trained language model built on the transformer architecture and trained jointly on text from dozens to over one hundred languages. Models such as mBERT and XLM-RoBERTa learn shared cross-lingual representations, enabling zero-shot or few-shot transfer: a model fine-tuned on English data can often be applied directly to French, German, Arabic, or Chinese without language-specific labels.	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.