Methods › Natural Language Processing › Contextualized Word Embeddings

Contextualized Word Embeddings

5 methods 280 papers tagged archive 2025-07-28

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 5 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.

ELMo – 234
USE Multilingual Universal Sentence Encoder – 26
CoVe Contextual Word Vectors – 13
Mirror-BERT – 6
context2vec – 6