Deep NLP Framework at LinkedIn (Mon, Oct 19 · 10:30 PM GMT+5:30)

This is online AI tech talk event, you can join from anywhere with zoom, please register and attend here: https://learn.xnextcon.com/event/eventdetails/W2020101910

Abstract:
Deep learning-based NLP technologies like BERT (Bidirectional Encoder Representations from Transformers) have recently made headlines for showing significant improvements in areas such as semantic understanding when contrasted with prior NLP techniques. However, exploiting the power of BERT in search and recommender systems is a non-trivial task, due to the heavy computation cost of BERT models.

To provide a unified technical solution, we developed DeText, a state-of-the-art open source NLP framework for text understanding. In this talk, we will introduce DeText, with live demo. We will discuss:

1) Overview on DeText
2) Technical architecture and design of DeText
3) Illustration of how neural ranking is designed and developed in DeText
4) Live demo

Workshop: Develop Customized Neural Nets – Forecasting and Predictive Modeling ( Thu, Oct 22 · 10:30 PM GMT+5:30)

Please register and attend:
https://learn.xnextcon.com/event/eventdetails/W20102210

In this workshop, we will discuss both theoretical concepts on deep learning, and hand-on code lab.

We will start with a technical talk on deep learning core concepts like loss functions, dropout rate, batch size, learning rate, and etc…

After the technical talk, we will walk through a hands on code lab where we will cover how to develop, deploy, tune your custom neural nets. Create your custom neural net by setting those options and optimizing for your domain.

[10:30 – 10:40 pm] Welcome and workshop overview
[10:40 – 11:15 pm] Overview on deep learning core concepts
[11:15 – 12:15 am] Hands on code lab
[12:15 – 12:30 am] Q&A and wrap up