Transformer models: an introduction and catalog — 2022 Edition
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
Deep Learning over the Internet: Training Language Models Collaboratively
Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, the World’s Largest and Most Powerful Generative Language Model
The Definitive Guide to Embeddings
NVIDIA Announces TensorRT 8 Slashing BERT-Large Inference Down to 1 Millisecond
Google Replaces BERT Self-Attention with Fourier Transform: 92% Accuracy, 7 Times Faster on GPUs
A Deep Dive Into Machine Translation
When BERT Plays The Lottery, All Tickets Are Winning
Training BERT at a University
Shrinking massive neural networks used to model language
What’s new in TensorFlow Lite for NLP
Domain-specific language model pretraining for biomedical natural language processing – Microsoft Research
TaBERT: A new model for understanding queries over tabular data
How Smart is BERT? Evaluating the Language Model’s Commonsense Knowledge
Smaller, faster, cheaper, lighter: Introducing DilBERT, a distilled version of BERT
Intel® Nervana™ NNP-I Shows Best-in-Class Throughput on BERT NLP Model – Intel AI
ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations
What does a Fine-tuned BERT model look at ?.
Understanding searches better than ever before
Give Me Jeans not Shoes: How BERT Helps Us Deliver What Clients Want | Stitch Fix Technology – Multithreaded
Learning Cross-Modal Temporal Representations from Unlabeled Videos
Habana Labs Goya Delivers Inferencing on BERT – Habana

Subscribe to our Digest