Deep dive into state of art NLP Implementations using the HuggingFace Library

Please note the location for this event - it is NOT the usual ScienceLogic location.

Parking will be validated. Please refer the note below about parking :

"Our office is conveniently located just across the street from the Wiehle - Reston East metro station on the Silver Line. If arriving by car, please take a parking ticket and park in either of the 2 lots adjacent to our building. After you park, please enter the building through the front entrance and please make sure you bring your ticket inside to be validated by our receptionist."

Speaker Profile:

Leonardo Apolonio is a machine learning engineer at Clarabridge, where he solves natural language processing (NLP) tasks, like detecting emotion, call reason, and expressed effort in the customer experience domain. He has experience maintaining and improving NLP pipelines to extract entities and topics from over 30 million websites daily, using the latest NLP and deep learning techniques. Leonardo has built scalable analytics techniques for anomaly detection using datasets with billions of events.

Abstract: Deep dive into state of art NLP Implementations using the HuggingFace Library

HuggingFace is building open-source tools and centralizing state of the art model implementations for natural language processing/understanding in Tensorflow and Pytorch. Leonardo will go over the latest model added to the library, text-to-text transformer (T5). Demonstrate the internal process that HuggingFace uses to translate models between frameworks and review the practical uses of these models.

Agenda:

06:00 - 06:15 : Meet and greet attendees
06:15 - 06:30 : Meetup Introductions and announcements
06:30 - 0800: Presentation

Review T5: Closing a chapter on transformer research "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
https://towardsdatascience.com/t5-a-model-that-explores-the-limits-of-transfer-learning-fb29844890b7

Learn Tensorflow and Pytorch at the same time! Review of HuggingFace Transformers library
https://medium.com/huggingface/from-tensorflow-to-pytorch-265f40ef2a28

Inference Benchmarks:
https://medium.com/huggingface/benchmarking-transformers-pytorch-and-tensorflow-e2917fb891c2

Thank you, Clarabridge, for being the sponsor for this event.