Methods › Natural Language Processing › Word Embeddings
Word Embeddings
Self-Supervised Learning refers to a category of methods where we learn representations in a self-supervised way (i.e without labels). These methods generally involve a pretext task that is solved to learn a good representation and a loss function to learn with. Below you can find a continuously updating list of self-supervised methods.
Methods
All 15 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.
| GloVe GloVe Embeddings | – | 357 |
| fastText | – | 240 |
| ELMo | – | 234 |
| UNITER UNiversal Image-TExt Representation Learning | – | 23 |
| Skip-gram Word2Vec | – | 14 |
| CoVe Contextual Word Vectors | – | 13 |
| Cross-View Training | – | 8 |
| TWEC Temporal Word Embeddings with a Compass | – | 7 |
| CBoW Word2Vec Continuous Bag-of-Words Word2Vec | – | 6 |
| Mirror-BERT | – | 6 |
| context2vec | – | 6 |
| Categorical Modularity | – | 1 |
| Comparative Analysis of Word Embedding Models in NLP Tasks | – | 1 |
| Poincaré Embeddings | – | 1 |
| lda2vec | – | 1 |