BERT
BERT pretrains deep bidirectional Transformer representations using masked language modeling. Fine-tuning the same pretrained encoder produced strong reported results across multiple language-understanding tasks.
Overview. BERT pretrains deep bidirectional Transformer representations using masked language modeling.
Context. Fine-tuning the same pretrained encoder produced strong reported results across multiple language-understanding tasks.
Claims and evidence
Claim ledger, 2BERT pretrains deep bidirectional Transformer representations using masked language modeling.
Fine-tuning the same pretrained encoder produced strong reported results across multiple language-understanding tasks.