Course Curriculum
10 interactive lessons with real-time autograding
1
Module 1
Introduction to spaCy
Industrial-strength NLP, pipelines, language models, and nlp() object.
2
Module 2
Tokens, Docs & Spans
Core data structures: Doc container, Token attributes, and Span slicing.
3
Module 3
Linguistic Features
POS tags, fine-grained morphology, lemmas, and stop words.
4
Module 4
Dependency Parsing
Syntactic trees, heads, dependencies, and noun chunks extraction.
5
Module 5
Named Entity Recognition
Doc.ents, entity labels, displaCy visualization, and IOB tagging.
6
Module 6
Rule-Based Matching
Matcher and PhraseMatcher for pattern discovery and entity linking.
7
Module 7
Word Vectors & Similarity
Static word embeddings, cosine similarity, and semantic comparison.
8
Module 8
Processing Pipelines
Custom pipeline components, nlp.pipe batching, and extension attributes.
9
Module 9
Text Classification
Training textcat architectures, binary, and multi-label classifiers.
10
Module 10
Custom NER Training
Training config, DocBin format, transfer learning, and model evaluation.