Enterprise AF solution for text classification (using BERT)

Leonardo Apolonio (Clarabridge)

9:00am–12:30pm Tuesday, October 29, 2019

Location: Grand Ballroom H

TensorFlow in ML research

Average rating:

(2.00, 1 rating)

Who is this presentation for?

Machine learning engineers, data scientists, and tech leads

Level

Intermediate

Description

Today we have machine learning engineers, software engineers, and data scientists. The trend in deep learning is that models are getting so powerful that there’s little need to know about the details of the specific algorithm, and instead the models can be immediately applied to custom use cases. Leonardo Apolonio explains how this trend will turn a machine learning engineer’s job into a software engineer’s skill.

Outline:

What is BERT?
Why is BERT important?
Fine-tuning BERT using AG News Dataset
Writing TensorFlow Serving Client
Building Docker containers for TensorFlow-Serving and a TensorFlow-Serving client
Building Docker containers and push containers to Docker Hub
Creating a Kubernetes cluster and deploy containers to Kubernetes in Google Cloud

Prerequisite knowledge

Familiarity with Python
A working knowledge of TensorFlow and Kubernetes

Materials or downloads needed in advance

A laptop
Google Cloud and Docker Hub accounts

What you'll learn

Learn how to use TensorFlow, Kubernetes on Google Cloud, and BERT (pretrained models)

Leonardo Apolonio

Clarabridge

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 also built scalable analytics techniques for anomaly detection using datasets with billions of events.