Learn about tokenization, entity recognition, and syntactic parsing using spaCy to apply NLP techniques.

Mastering Natural Language Processing

This module extensively introduces the widely-used Python library, spaCy, for natural language processing (NLP). It covers spaCy basics, such as tokenization and part-of-speech tagging, as well as advanced topics like custom model training and NLP pipeline creation.

This module has three parts. Part 1 focuses on spaCy’s fundamentals, architecture, installation, and setup. It teaches common NLP tasks like tokenization, named entity recognition (NER), part-of-speech (POS) tagging, and dependency parsing.

Part 2 delves into spaCy’s features, covering syntax, and semantics. It explores pattern matching and semantics via word vectors and thoroughly discusses statistical information extraction techniques. In part 3, we’ll examine several advanced topics, such as discussing the development of complex NLP models requiring expertise, analysis, and practical experiences. We will also conduct multiple experiments with various NLP tasks, including customizing statistical models to meet specific needs.

Mastering spaCy

In this chapter, you worked with word vectors, which are floating-point vectors that represent word semantics:


- We learned about the different ways to perform text vectorization.

- We learned how to use word vectors and distributed semantics.


- We explored the vector operations that word vectors allow and what semantics these operations bring.






Getting Started

Core Operations with spaCy

Linguistic Features

Rule-Based Matchmaking

Working with Word Vectors and Semantic Similarity

Putting Everything Together: Semantic Parsing with spaCy

Assessment: spaCy Features

Customizing spaCy Models

Text Classification with spaCy

spaCy and Transformers

Putting Everything Together: Designing a Chatbot with spaCy

Appendix

Assessment - Machine Learning with spaCy

Conclusion

Summary: Word Vectors and Semantic Similarity

Key takeaways