Build upon your foundational knowledge of natural language processing by exploring more complex topics.
Overview
Syllabus
Introduction
- Elevate Your NLP expertise using Python and machine learning
- What you should know
- How to use the challenge exercise files
- Overview of natural language processing
- Evolution of natural language processing
- Natural language processing libraries
- Introduction to spaCy
- Challenge: Build a spaCy processing pipeline
- Solution: Build a processing pipeline
- Analyze customer feedback using spaCy
- The spaCy processing pipeline
- Challenge: Analyze customer feedback
- Solution: Analyze customer feedback
- Modern natural language processing
- Transformers neural networks
- Large language models: BERT, GPT
- Challenge: Sentiment analysis using DistilBERT
- Solution: Sentiment analysis using DistilBERT
- Methods that improve LLM performance
- Supervised fine-tuning
- Fine-tuning methods
- Retrieval-augmented generation (RAG)
- Parameter-efficient fine-tuning (PEFT)
- Challenge: Parameter-efficient fine-tuning with LoRa
- Solution: Parameter-efficient fine-tuning with LoRa
- Next steps
Taught by
Gwendolyn Stripling