Concept
Masked language modeling
Masked language modeling (MLM) is a self-supervised training objective where you hide a fraction of the tokens in a sequence and train the model to predict them from the surrounding context on both sides.
The rest of “Masked language modeling” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→