Feature: Entity and span ruler
Feature: Part-of-speech tagger
Feature: Token-to-vector layer and pretraining
Feature: Training utils, Example, Corpus and converters
Feature: User experience, error messages etc.
Feature: Word vectors and similarity
Feature: Built-in displaCy and other visualizers
Contributions welcome! (also suited for spaCy beginners)
Invalid issues: typos, mistakes etc.
Issues related to Jupyter notebook environments
Afrikaans language data and models
Amharic language data and models
Arabic language data and models
Azerbaijani language data and models
Bulgarian language data and models
Bengali language data and models
Catalan language data and models
Czech language data and models
Danish language data and models
German language data and models
Lower Sorbian language data and models
Greek language data and models