Part-of-Speech Tagging Tutorial Section

Part-of-Speech Tagging

Discover Part-of-Speech (POS) tagging and how to extract linguistic structure and word grammar from text.

Part-of-Speech (POS) Tagging

Part-of-Speech (POS) tagging is the process of marking up a word in a text corpus to a corresponding grammatical part of speech, based on both its definition and its context alongside adjacent words. This is a critical step for Syntactic Analysis.

POS Breakdown Example

The
Determiner

quick
Adjective

brown
Adjective

fox
Noun

jumps
Verb

over
Preposition

the
Determiner

lazy
Adjective

dog
Noun

                            Why POS Tagging?
                            Word Sense Disambiguation: Tells the difference between "I like to bear (Verb) weight" and "I saw a brown bear (Noun)".
Lemmatization: Feeds into lemmatizers to provide context.
Named Entity Recognition: Proper Nouns (NNP) are crucial flags for identifying people, cities, and companies.

                        

Penn Treebank POS Tags

Most modern datasets are trained using the Penn Treebank tagset.

Tag	Description	Examples
NN	Noun, singular	dog, truth, time
NNP	Proper noun	London, John
VB	Verb, base form	run, eat, be
VBD	Verb, past tense	ran, ate, was
JJ	Adjective	happy, large
RB	Adverb	quickly, very
IN	Preposition	in, of, under

Implementation with spaCy

spaCy is highly optimized and widely used in industry for POS tagging and dependency parsing. It returns both universal tags (POS) and detailed tags (TAG).

POS Tagging with spaCy

import spacy

# Load the small English language model
nlp = spacy.load("en_core_web_sm")

text = "Apple is looking at buying U.K. startup for $1 billion"
doc = nlp(text)

# Token text, POS tag, and detailed explanation
print(f"{'Text':<12} | {'Tag':<8} | {'Detailed POS Description'}")
print("-" * 50)

for token in doc:
    print(f"{token.text:<12} | {token.pos_:<8} | {spacy.explain(token.pos_)}")

# Output Sample:
# Apple        | PROPN    | proper noun
# is           | AUX      | auxiliary
# looking      | VERB     | verb
# at           | ADP      | adposition
# buying       | VERB     | verb
# U.K.         | PROPN    | proper noun
# startup      | NOUN     | noun

Previous: Lemmatization