spaCy: Dependency Parsing

• syntactic dependency parser
• API for navigating the tree
• sentence boundary detection
• iterate over base noun phrases, or “chunks”

Noun chunks

• = base noun phrases – flat phrases that have a noun as their head
• noun plus the words describing the noun:

the lavish green grass

or

the world’s largest tech fund

• To get the noun chunks in a document, simply iterate over Doc.noun_chunks

…

Navigating the parse tree

import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("Autonomous cars shift insurance liability toward manufacturers")
for token in doc:
    print(
        token.text,
        token.dep_,
        token.head.text,
        token.head.pos_,
        [child for child in token.children]
    )

• every word has exactly one head

 

Zdroje

• https://spacy.io/usage/linguistic-features#dependency-parse