Session

Implementing natural language processing (NLP) models just got simpler and faster. In this talk, we introduce BERT (Bidirectional Encoder Representation from Transformers), a state-of-the-art (SOTA) NLP model, and demonstrate how it can be used for various NLP tasks. Learn how to implement NLP models to quickly prototype products, validate new ideas, and learn SOTA NLP. And at the end we will also demo how we can use PyTorch with Amazon SageMaker to fine-tune the BERT model and deploy it with Elastic Inference.