Applied AI: Building NLP Apps with Hugging Face Transformers

Learn how to build natural language processing (NLP) applications with pretrained transformers in Hugging Face, the popular machine learning platform.

Introduction

• Building NLP apps with Transformers
• Course coverage and prerequisites
• Setting up the exercise files

1. Question-Answering (Qu-An)

• Question-answering in NLP
• Types of question-answering
• Building a Qu-An pipeline
• The SQuAD metric
• Evaluating Qu-An performance

2. Text Summarization

• Text summarization in NLP
• The BART model architecture
• Summarization with pipelines
• The ROUGE score
• Evaluating with ROUGE

3. Natural Language Generation

• Natural language generation in NLP
• Content creation with Transformers
• Conversation generation
• Chatbot conversation example
• Machine translation in NLP
• Translating with Hugging Face Transformers

4. Customizing Models with Transfer Learning

• Training a custom model
• Loading a Hugging Face dataset
• Encoding and preprocessing the dataset
• Customizing the model architecture
• Training the sentiment model
• Predicting with the custom model

5. Deploying and Using Hugging Face Models

• Inference challenges with Transformers
• Customizing pretrained models
• Model compression overview
• Serving multiple models

Conclusion

• Continuing with Hugging Face