Advanced NLP with Python for Machine Learning

Course details

This course is for anyone who wants to learn more advanced NLP methods. Instructor Gwendolyn Stripling, PhD, begins with a look at the fundamental concepts and principles of NLP, including the evolution and significance of natural language processing. She then reviews some NLP and Python basics—and introduces the NLP library spaCy—before jumping into more modern techniques and advancements in natural language processing using Transformer Models like GPT and BERT. Methods such as supervised fine-tuning, parameter efficient fine-tuning (PEFT), and retrieval-augmented generation (RAG) give you the foundational knowledge you need to improve large language model (LLM) performance. Learn the ways you can apply NLP in your applications and day-to-day, including how to analyze customer sentiments Each chapter ends with a challenge and solution, so you can test your knowledge as you go.

Concepts

0. Introduction

01 - Elevate Your NLP expertise using Python and machine learning
02 - What you should know
03 - How to use the challenge exercise files

1. Introduction to NLP Libraries

04 - Overview of natural language processing
05 - Evolution of natural language processing
06 - Natural language processing libraries

2. Review NLP and Python Basics

07 - Introduction to spaCy
08 - Challenge - Build a spaCy processing pipeline
09 - Solution - Build a processing pipeline

3. Using spaCy for Customer Feedback Analysis

10 - Analyze customer feedback using spaCy
11 - The spaCy processing pipeline
12 - Challenge - Analyze customer feedback
13 - Solution - Analyze customer feedback

4. Modern NLP - Transformers and Large Language Models

14 - Modern natural language processing
15 - Transformers neural networks
16 - Large language models - BERT, GPT
17 - Challenge - Sentiment analysis using DistilBERT
18 - Solution - Sentiment analysis using DistilBERT

5. Methods That Improve LLM Performance

19 - Methods that improve LLM performance
20 - Supervised fine-tuning
21 - Fine-tuning methods
22 - Retrieval-augmented generation (RAG)
23 - Parameter-efficient fine-tuning (PEFT)
24 - Challenge - Parameter-efficient fine-tuning with LoRa
25 - Solution - Parameter-efficient fine-tuning with LoRa

Conclusion

26 - Next steps