手法を比較

	多言語Vision Transformer	多言語文埋め込み
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2021–2023	2019–2022
提唱者	Dosovitskiy et al. (ViT base); multilingual extension by multiple groups (2021–2023)	Reimers, N. & Gurevych, I.; Feng, F. et al. (Google)
種類	Transformer-based vision model with multilingual capabilities	Cross-lingual representation learning
原典	Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR 2021).	Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525.
別名	Multilingual ViT, Cross-lingual Vision Transformer, Multilingual Visual Transformer, ML-ViT	multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings
関連	4	5
概要	Multilingual Vision Transformer (Multilingual ViT) extends the Vision Transformer architecture to operate across multiple languages, enabling image understanding and image-text reasoning in multilingual or cross-lingual settings. It combines patch-based image encoding with multilingual text representations, allowing a single model to serve diverse linguistic communities for tasks such as image captioning, visual question answering, and cross-lingual image retrieval.	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.