Pre-Trained Language Models: Tools/Frameworks to Solve Downstream NLP/NLU Tasks, Wed, Jan 25, 2023, 8:00 AM

NOTE: THIS IS AN EARLY TIME SLOT SESSION - repeated on Thu Jan 26 at 3:30-4:30 pm ET. This a follow-up to the "Pre-Trained Language Models: A New Standard for NLU Tasks" sessions held on Jan 18 & 19, 2023, where we introduced pre-trained language models and explained how they have become a new standard for solving various NLP tasks. In this session, we will start with a quick recap of the previous session and then do a deep dive into the tools and frameworks for loading and fine-tuning pre-trained language models. We will load models from the HuggingFace Model Hub https://huggingface.co/models and fine-tune them on a public dataset to solve a downstream NLP task using a small dataset and a few training steps. Reza Fazeli is a conversational AI engineer for Watson Assistant, working closely with IBM Research teams to develop and deploy algorithms for improving our virtual assistant products.