BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding - Crossminds
CrossMind.ai logo
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT is the first deeply bidirectional, unsupervised language representation model, pre-trained using only a plain text corpus. It has been widely used on various natural language processing tasks. This graph maps prior contextual representation models it builds on and notable pre-trained language models derived from BERT.
Top related arXiv papers
Key knowledge areas
Other recommended papers

Andrew M. Dai, Semi-supervised Sequence Learning. NIPS 2015

Rowan Zellers, Defending Against Neural Fake News. NeurIPS 2019

Guillaume Lample, Cross-lingual Language Model Pretraining. NeurIPS 2019

C. Sun, VideoBERT: A Joint Model for Video and Language Representation Learning. 2019 IEEE/CVF International Conference on Computer Vision (ICCV) 2019