Google posts the BERT paper on arXiv
BERT paper posted on arXiv — pre-training a deep bidirectional Transformer encoder that conditions on both left and right context
Why it matters
Fine-tuned with just one additional output layer, it set new state-of-the-art results on 11 NLP tasks, including GLUE 80.4% and SQuAD v1.1 F1 93.2 (as reported by the authors)
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/1810.04805Added in Week 41, 2026 · See that week