Сравнение методов

	Многоязычный анализ тональности	Многоязычные вложения предложений
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2004–2020	2019–2022
Автор метода	Pang, B. & Lee, L. (early sentiment analysis); cross-lingual extension via mBERT/XLM-R community (2019–2020)	Reimers, N. & Gurevych, I.; Feng, F. et al. (Google)
Тип	Supervised classification / fine-tuned LM	Cross-lingual representation learning
Основополагающий источник	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. Proceedings of ACL 2020, 8440–8451.	Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525.
Другие названия	cross-lingual sentiment analysis, multilingual opinion mining, multilingual sentiment classification, MSA	multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings
Связанные	5	5
Сводка	Multilingual Sentiment Analysis (MSA) applies deep learning — most commonly a fine-tuned multilingual language model such as mBERT or XLM-RoBERTa — to classify the sentiment polarity (positive, negative, neutral) of text written in two or more languages, enabling opinion mining across language boundaries without building separate models per language.	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.