- This event has passed.
[Webinar] HuggingFace NLP models for Contract Review + NVIDIA DALI
October 18, 2021 @ 12:00 pm - 1:00 pm EDT
Zoom link: https://us02web.zoom.us/j/82308186562
Talk #1: Introductions and Meetup Announcements (Chris Fregly and Antje Barth)
Talk #2: Leveraging Hugging Face on SageMaker to create NLP Models for Contract Review
Speakers:
Aaron Sengstacken, ML Specialist Solutions Architect @ AWS
Heiko Hotz, NLP Domain Lead, Solutions Architect for AI/ML @ AWS
Abstract: Contract review is the process of thoroughly reading a contract to understand the rights and obligations of an individual or company signing it and assessing the associated impact. It usually takes many hours, is expensive, and therefore an inefficient use of a legal professional’s time and skills. With the latest advances in NLP, machine learning models can learn to automatically extract and identify key clauses from contracts. In this demo we show how to set up and leverage such an NLP model to quickly extract key information from a contract, thus saving hundreds of hours of manual labour.
Talk #3: Address Data Pre-processing Bottleneck in Training CV models with Amazon SageMaker — Leveraging NVIDIA DALI and SageMaker Debugger
Speaker:
Sayon Kumar Saha, ML Specialist Solutions Architect @ AWS
Abstract: Training of computer vision (CV) models often require multi-stage heavy data pre-processing that are natively executed on the CPUs. This often becomes a bottleneck causing the expensive GPU resources to starve for data. This session discusses some best-practices to handle this and then dives into an Amazon SageMaker training example with benchmark results. A PyTorch example with RESNET models of different complexities is demonstrated to identify bottlenecks with Amazon SageMaker Debugger and compare performance gains by offloading JPEG decodings and heavy augmentations to available GPUs using NVIDIA DALI.
Speaker Bio: Sayon Kumar Saha is a Machine Learning Specialist Solutions Architect at AWS, based in Berlin, Germany. Sayon focuses on helping AWS customers design and deploy ML solutions in production. Prior to joining AWS, he worked in the data science and engineering space at trivago, SAP and DFKI. He is passionate about the use of ML to solve business problems across various industries. In his spare time, he loves to travel, explore cultures and cuisines, and is passionate about photography.
Related Links
=============
O’Reilly Book: https://www.amazon.com/dp/1492079391/
Website: https://datascienceonaws.com
Meetup: https://meetup.datascienceonaws.com
GitHub Repo: https://github.com/data-science-on-aws/
YouTube: https://youtube.datascienceonaws.com
Slideshare: https://slideshare.datascienceonaws.com
