Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Vícejazyčné LSTM× | Vícejazyčná vektorová reprezentace vět× | |
|---|---|---|
| Obor | Hluboké učení | Hluboké učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 1997 (LSTM); multilingual NLP applications from ~2016 | 2019–2022 |
| Tvůrce≠ | Hochreiter, S. & Schmidhuber, J. (LSTM base); multilingual application by the NLP community from ~2016 | Reimers, N. & Gurevych, I.; Feng, F. et al. (Google) |
| Typ≠ | Recurrent neural network (sequence model) | Cross-lingual representation learning |
| Původní zdroj≠ | Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525. link ↗ |
| Další názvy | Multilingual LSTM, Cross-lingual LSTM, Multi-language LSTM, Multilingual Recurrent Network | multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings |
| Příbuzné | 5 | 5 |
| Shrnutí≠ | A Multilingual LSTM is a Long Short-Term Memory recurrent network trained or fine-tuned to process sequences in multiple languages, typically by sharing a single model across language-specific or joint subword embeddings. It captures long-range dependencies in text and is applied to multilingual classification, named entity recognition, sentiment analysis, and sequence labeling. | 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. |
| ScholarGateDatová sada ↗ |
|
|