Statistical Models

Advanced NLP with spaCy

Ines Montani

spaCy core developer

What are statistical models?

Enable spaCy to predict linguistic attributes in context
- Part-of-speech tags
- Syntactic dependencies
- Named entities
Trained on labeled example texts
Can be updated with more examples to fine-tune predictions

Model Packages

A package with the label en_core_web_sm

import spacy

nlp = spacy.load('en_core_web_sm')

Binary weights
Vocabulary
Meta information (language, pipeline)

Predicting Part-of-speech Tags

import spacy

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

# Process a text
doc = nlp("She ate the pizza")

# Iterate over the tokens
for token in doc:

    # Print the text and the predicted part-of-speech tag
    print(token.text, token.pos_)

She PRON
ate VERB
the DET
pizza NOUN

Predicting Syntactic Dependencies

for token in doc:
    print(token.text, token.pos_, token.dep_, token.head.text)

She PRON nsubj ate
ate VERB ROOT ate
the DET det pizza
pizza NOUN dobj ate

Visualization of the dependency graph for "She ate the pizza"

Label	Description	Example
nsubj	nominal subject	She
dobj	direct object	pizza
det	determiner (article)	the

Predicting Named Entities

Visualization of the named entities in "Apple is looking at buying U.K. startup for $1 billion"

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

# Iterate over the predicted entities
for ent in doc.ents:

    # Print the entity text and its label
    print(ent.text, ent.label_)

Apple ORG
U.K. GPE
$1 billion MONEY

Tip: the explain method

Get quick definitions of the most common tags and labels.

spacy.explain('GPE')

Countries, cities, states'

spacy.explain('NNP')

'noun, proper singular'

spacy.explain('dobj')

'direct object'

Let's practice!

Advanced NLP with spaCy