In this spaCy NLP course, you will learn about core tasks like tokenization, NER, and POS tagging and advanced topics such as custom model training and complex NLP pipelines.

jupyter.tar.gz

jupyter

spacy-code

This course 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. 

The course 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. 

Part 3 examines advanced topics, including developing complex NLP models that require expertise, analysis, and practical experience. Multiple experiments with various NLP tasks are conducted, including customizing statistical models to meet specific needs.

Mastering spaCy

import spacy
from spacy.matcher import Matcher

nlp = spacy.load("en_core_web_md")

pattern = [{"IS_DIGIT": True, "LENGTH": 4}, {"TEXT": "-"}, {"IS_DIGIT": True, "LENGTH": 2}, {"TEXT": "-"}, {"IS_DIGIT": True, "LENGTH": 2}]

# Create a Spacy Matcher object and add the pattern to it
matcher = Matcher(nlp.vocab)
matcher.add("DATE_PATTERN", [pattern])

doc = nlp("I have a meeting on 2022-02-15 and another meeting on 2022-02-20")

# Match the defined pattern against the processed document and print out the matched spans
matches = matcher(doc)
for match_id, start, end in matches:
    matched_span = doc[start:end]
    print(matched_span.text)


Let's look at the solution to the previous exercise.

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

Conclusion

Assessment - Machine Learning with spaCy

Solution: Rule-Based Matchmaking

Solution