Part-of-Speech Tagging
Part-of-speech (POS) tagging identifies the grammatical category of each word. spaCy provides both Universal (coarse) and Detailed (fine-grained) tags.
Universal POS Tags
Open Class Words (content words)
- NOUN – Noun
- VERB – Verb
- ADJ – Adjective
- ADV – Adverb
- PROPN – Proper Noun
- INTJ – Interjection (oh, wow, oops)
Closed Class Words (function words)
- DET – Determiner (the, a, this)
- ADP – Adposition: prepositions and postpositions (in, to, during)
- PRON – Pronoun
- NUM – Numeral
- AUX – Auxiliary
- CCONJ – Coordinating Conjunction (and, or, but)
- SCONJ – Subordinating Conjunction (if, while, because)
- PART – Particle (not, 's, to in infinitives)
Other
- PUNCT – Punctuation
- SYM – Symbol ($, %, @)
- X – Other (foreign words, typos)
Detailed Tags (Penn Treebank)
Fine-grained English-specific tags
- NN – Noun, Singular; NNS – Noun, Plural
- NNP – Proper Noun, Singular; NNPS – Proper Noun, Plural
- VB – Verb, Base Form
- VBD – Verb, Past Tense
- VBG – Verb, Gerund/Present Participle
- VBN – Verb, Past Participle
- VBP – Verb, Non-3rd Person Singular Present
- VBZ – Verb, 3rd Person Singular Present
- JJ – Adjective; JJR – Adjective, Comparative; JJS – Adjective, Superlative
- RB – Adverb; RBR – Adverb, Comparative; RBS – Adverb, Superlative
- PRP – Personal Pronoun; PRP$ – Possessive Pronoun
- DT – Determiner
- IN – Preposition or Subordinating Conjunction
- CC – Coordinating Conjunction
- CD – Cardinal Number