Noun chunking is the task of identifying a noun and the words directly related to it. More specifically, with respect to the LatinCy pipeline, it is using annotations of the POS-tagger (tagger) and the dependency parser (parser) to identify all children of a token tagged as NOUN. Unlike the NLP tasks in the preceding sections, this task cannot be associated directly with a pipeline component; rather it is a special Span case defined in the spaCy language model itself under syntax iterators.
# Imports & setup
import spacy
from pprint import pprint
nlp = spacy.load('la_core_web_lg')
text = "Haec narrantur a poetis de Perseo. Perseus filius erat Iovis, maximi deorum. Avus eius Acrisius appellabatur."
doc = nlp(text)
print(doc)Haec narrantur a poetis de Perseo. Perseus filius erat Iovis, maximi deorum. Avus eius Acrisius appellabatur.As defined in the syntax_iterators, noun chunks become attributes of the spaCy Doc object. Noun chunks will return any token span for which the dependency head has the NOUN tag. A one-word noun chunk is just the noun itself, so not of particular interest. So, really what we are looking for are longer spans of noun-related text.
# Print the noun chunks in the text
for noun_chunk in doc.noun_chunks:
if len(noun_chunk) > 1:
print(noun_chunk)maximi deorum
Avus eiusspaCy Noun chunks