Building NLP Pipelines with spaCy
1h 1mAdvanced2023-04-25
Authors
Prateek Sawhney
AI Engineer at CM1 GmbH, GitHub Campus Expert
Course details
Are you looking to learn more about the key features and functionalities built into spaCy? Look no further. It’s time to get up to speed with using the extensive spaCy library to solve complex natural language processing tasks. Join instructor Prateek Sawhney in this advanced skills development course, as he demonstrates business-critical approaches and techniques to solving problems in rule-based AI and machine learning.
Learn the basics of how to leverage the complex and advanced spaCy library to address real-world technical problems. From text processing to data analysis, processing pipelines, and training an artificial neural network, Prateek helps you get up and running quickly with results-driven problem-solving tasks. Along the way, you can test out your new skills in the exercise challenges at the end of each section.
Learn the basics of how to leverage the complex and advanced spaCy library to address real-world technical problems. From text processing to data analysis, processing pipelines, and training an artificial neural network, Prateek helps you get up and running quickly with results-driven problem-solving tasks. Along the way, you can test out your new skills in the exercise challenges at the end of each section.
Skills covered
spaCyExplosionNatural Language Processing (NLP)PythonArtificial Intelligence (AI)Open SourceDeep Dive (X:Y)
Concepts
0. Introduction
- 01 - Why use spaCy
- 02 - Prerequisites of the course
- 03 - How to install spaCy
1. Text Processing with spaCy
- 04 - Introduction to spaCy
- 05 - spaCy's statistical models
- 06 - spaCy's containers
- 07 - Introduction to matching based on rules
- 08 - Challenge - Predicting linguistic annotations
- 09 - Solution - Predicting linguistic annotations
2. Data Analysis Using spaCy
- 10 - spaCy's data structures
- 11 - Similarity and word vectors
- 12 - Integrating spaCy's models and rules
- 13 - Challenge - Phrase matching
- 14 - Solution - Phrase matching
3. Processing Pipelines with spaCy
- 15 - Processing pipelines
- 16 - Pipeline's custom components
- 17 - Extension attributes - Part 1
- 18 - Extension attributes - Part 2
- 19 - Performance and scaling
- 20 - Challenge - Processing streams and selective processing
- 21 - Solution - Processing streams and selective processing
4. Training an Artificial Neural Network
- 22 - Training and updating models
- 23 - Training loop
- 24 - Challenge - Building a training loop
- 25 - Solution - Building a training loop
- 26 - Training loop best practices
- 27 - Challenge - Training multiple labels
- 28 - Solution - Training multiple labels
Conclusion
- 29 - Wrap-up
Related courses
- Natural Language Processing (NLP) on Amazon Bedrock
- GraphRAG Essential Training
- Data Preparation, Feature Engineering, and Augmentation for AI Models
- Knowledge Graph Data Engineering for Generative AI Use Cases
- Automated Financial Reporting with AI
- SQL for AI Projects: From Data Exploration to Impact
- AI Show: Building NLP models with Azure ML AutoML
- Applied AI: Building NLP Apps with Hugging Face Transformers
Related learn paths
- Advance Your Skills in Natural Language Processing
- Generative AI Professional Certificate by Snowflake
- Advance Your Skills in AI and Machine Learning
- Moving from Data Scientist to Data Analyst
- Fundamentals to Become a Machine Learning Engineer
- Develop Your Skills with Large Language Models
- Building Generative AI Skills for Developers
- Applying Generative AI as a Business Professional