Named tools and model families · MLD-0113
BERT
A transformer-encoder model family pretrained using masked-token objectives to learn bidirectional text representations.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Adapt contextual representations for text classification.
Original caveat
BERT is not a standard left-to-right chat generator.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Deployment.
Tags: DL · NLP.
Aliases: Bidirectional Encoder Representations from Transformers.