Transfer Learning for NLP with TensorFlow Hub

Welcome to this hands-on project on transfer learning for natural language processing with TensorFlow and TF Hub. By the time you complete this project, you will be able to use pre-trained NLP text embedding models from TensorFlow Hub, perform transfer learning to fine-tune models on real-world data, build and evaluate multiple models for text classification with TensorFlow, and visualize model performance metrics with Tensorboard.

Project-based Course Overview

Welcome!

Welcome to Transfer Learning for NLP with TensorFlow Hub. This is a project-based course which should take approximately 1.5 hours to complete. Before diving into the project, please take a look at the course objectives and structure:

Course Objectives

In this course, we are going to focus on three learning objectives:

• Use pre-trained NLP text embedding models from TensorFlow Hub

• Perform transfer learning to fine-tune models on real-world text data

• Visualize model performance metrics with TensorBoard

This is a hands-on project on transfer learning for natural language processing with TensorFlow and TF Hub. By the time you complete this project, you will be able to use pre-trained NLP text embedding models from TensorFlow Hub, perform transfer learning to fine-tune models on real-world data, build and evaluate multiple models for text classification with TensorFlow, and visualize model performance metrics with Tensorboard.

Prerequisites: In order to successfully complete this project, you should be competent in the Python programming language, be familiar with deep learning for Natural Language Processing (NLP), and have trained models with TensorFlow or and its Keras API.

Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Course Structure

This course is divided into 3 parts:

1. Course Overview: This introductory reading material.

2. Transfer Learning for NLP with TensorFlow Hub: This is the hands on project that we will work on in Rhyme.

3. Graded Quiz: This is the final assignment that you need to pass in order to finish the course successfully.

Project Structure

The hands on project on Transfer Learning for NLP with TensorFlow Hub is divided into following tasks:

Task 1: Introduction to the Project Task 2: Setup your TensorFlow and Colab Runtime Task 3: Load the Quora Insincere Questions Dataset Task 4: TensorFlow Hub for Natural Language Processing
Tasks 5 & 6: Define Function to Build and Compile Models Task 7: Train Various Text Classification Models Task 8: Compare Accuracy and Loss Curves Task 9: Fine-tune Model from TF Hub Task 10: Train Bigger Models and Visualize Metrics with TensorBoard