Порівняння методів
Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.
| Багатомовний багатошаровий перцептрон× | Багатомовні векторні представлення речень× | |
|---|---|---|
| Галузь | Глибоке навчання | Глибоке навчання |
| Родина | Machine learning | Machine learning |
| Рік появи≠ | 2010s | 2019–2022 |
| Автор методу≠ | McCulloch & Pitts / Rumelhart et al. (MLP); multilingual application became standard in NLP from the 2010s onward | Reimers, N. & Gurevych, I.; Feng, F. et al. (Google) |
| Тип≠ | Feedforward neural network (multilingual variant) | Cross-lingual representation learning |
| Основоположне джерело≠ | Artetxe, M., & Schwartz, H. A. (2019). Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond. Transactions of the Association for Computational Linguistics, 7, 597–610. DOI ↗ | Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525. link ↗ |
| Інші назви | Multilingual MLP, cross-lingual MLP, multilingual feedforward network, multilingual FFNN | multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings |
| Пов'язані≠ | 4 | 5 |
| Підсумок≠ | A Multilingual MLP is a feedforward neural network trained on text from two or more languages, relying on shared or aligned input representations — such as multilingual word embeddings or subword vocabularies — so that a single model can process and classify text across languages without separate per-language networks. | 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. |
| ScholarGateНабір даних ↗ |
|
|