Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Kontrastivní učení pro NLP× | BERT Embeddings× | |
|---|---|---|
| Obor | Dolování textu | Dolování textu |
| Rodina | Process / pipeline | Process / pipeline |
| Rok vzniku≠ | 2020–2021 | 2019 |
| Tvůrce≠ | Gao, Yao & Chen (SimCSE, 2021); Khosla et al. (Supervised Contrastive, 2020) | Devlin, Chang, Lee & Toutanova (Google AI) |
| Typ≠ | Self-supervised / supervised representation learning | Contextual transformer text-representation method |
| Původní zdroj≠ | Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple Contrastive Learning of Sentence Embeddings. Proceedings of EMNLP 2021. link ↗ | Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186. DOI ↗ |
| Další názvy≠ | SimCSE, contrastive sentence embeddings, ContrastiveBERT, Karşıtlık Öğrenmesi — NLP (Contrastive Learning) | contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri |
| Příbuzné | 4 | 4 |
| Shrnutí≠ | Contrastive learning for NLP is a representation-learning technique — popularised by SimCSE (Gao et al., 2021) and Supervised Contrastive Learning (Khosla et al., 2020) — that trains a text encoder by pulling embeddings of similar text pairs together while pushing embeddings of dissimilar pairs apart. The result is a dense, high-quality embedding space that can be learned with no labels at all, or with minimal supervision, making it especially valuable when annotated data are scarce. | BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA. |
| ScholarGateDatová sada ↗ |
|
|